docsmith-mcp 0.0.1-beta.1

package/dist/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","names":["filePath: string","scriptPath: string","options: RunPythonFileOptions","runPyOptions: RunPyOptions","filePath: string","fileType: string","packages: Record<string, Record<string, string>>","scriptName: string","scriptArgs: string[]"],"sources":["../src/code-runner.ts","../src/utils.ts","../src/index.ts"],"sourcesContent":["/**\n * Code runner client - uses @mcpc-tech/code-runner-mcp npm package\n */\nimport { runPy, type RunPyOptions } from \"@mcpc-tech/code-runner-mcp\";\nimport { readFileSync } from \"fs\";\nimport { fileURLToPath } from \"url\";\nimport { dirname, join, resolve } from \"path\";\n\nconst __filename = fileURLToPath(import.meta.url);\nconst __dirname = dirname(__filename);\n\n/**\n * Options for running Python script files\n */\nexport interface RunPythonFileOptions {\n  /** Command line arguments to pass to the script */\n  args?: string[];\n  /** Package name mappings (import_name -> pypi_name) */\n  packages?: Record<string, string>;\n  /** Base directory for the script (default: \"python\") */\n  baseDir?: string;\n  /** User file paths that need to be accessible (for file system mounting) */\n  filePaths?: string[];\n}\n\n/**\n * Convert absolute file path to Pyodide virtual path\n * Determines the mount root and converts the path accordingly\n *\n * @param filePath - Absolute path to the file\n * @returns Object with mountRoot (host path) and virtualPath (Pyodide path)\n */\nfunction getFileSystemMapping(\n  filePath: string,\n): { mountRoot: string; virtualPath: string } {\n  const absolutePath = resolve(filePath);\n\n  // Mount the parent directory of the file\n  // This allows Python to access the file and its siblings\n  const mountRoot = dirname(absolutePath);\n  const virtualPath = absolutePath;\n\n  return { mountRoot, virtualPath };\n}\n\n/**\n * Run a Python script file using code-runner-mcp\n *\n * @param scriptPath - Path to the Python script (relative to baseDir)\n * @param options - Execution options\n * @returns The execution result\n */\nexport async function runPythonFile(\n  scriptPath: string,\n  options: RunPythonFileOptions = {},\n): Promise<any> {\n  const {\n    args = [],\n    packages = {},\n    baseDir = \"python\",\n    filePaths = [],\n  } = options;\n\n  // Read the Python script\n  const fullPath = join(__dirname, \"..\", baseDir, scriptPath);\n  const scriptContent = readFileSync(fullPath, \"utf-8\");\n\n  // Build wrapper code that sets sys.argv and executes the script\n  const wrapperCode = `\nimport sys\nimport json\n\n# Set command line arguments\nsys.argv = ['${scriptPath}'] + ${JSON.stringify(args)}\n\n# Execute the script\n${scriptContent}\n`;\n\n  // Determine mount root from the first file path\n  let mountRoot = join(__dirname, \"..\"); // Default: project root\n  if (filePaths.length > 0) {\n    const mapping = getFileSystemMapping(filePaths[0]);\n    mountRoot = mapping.mountRoot;\n  }\n\n  // Execute via runPy with options\n  // Mount point is the same as the mount root (Pyodide will see host paths directly)\n  const runPyOptions: RunPyOptions = {\n    packages,\n    nodeFSMountPoint: mountRoot,\n    nodeFSRoot: mountRoot,\n  };\n  const stream = await runPy(wrapperCode, runPyOptions);\n\n  // Read the stream output\n  const reader = stream.getReader();\n  const decoder = new TextDecoder();\n  let stdout = \"\";\n  let stderr = \"\";\n  let error = \"\";\n\n  try {\n    while (true) {\n      const { done, value } = await reader.read();\n      if (done) break;\n\n      const chunk = decoder.decode(value, { stream: true });\n      if (chunk.startsWith(\"[stderr] \")) {\n        stderr += chunk.slice(9);\n      } else if (chunk.startsWith(\"[err]\")) {\n        error += chunk;\n      } else {\n        stdout += chunk;\n      }\n    }\n  } catch (streamError) {\n    // Stream error means Python execution failed\n    return { error: String(streamError) };\n  }\n\n  // Check for errors\n  if (error) {\n    return { error: error.replace(/\\[err\\]\\[py\\]\\s*/g, \"\").trim() };\n  }\n\n  // Parse the JSON output from the script (last line)\n  const lines = stdout.trim().split(\"\\n\");\n  const lastLine = lines[lines.length - 1];\n\n  try {\n    return JSON.parse(lastLine);\n  } catch {\n    return { stdout, stderr };\n  }\n}\n","/**\n * Utility functions for document processing\n */\n\n/**\n * Detect file type from file extension\n */\nexport function detectFileType(\n  filePath: string,\n): \"excel\" | \"word\" | \"pdf\" | \"text\" | null {\n  const ext = filePath.toLowerCase().split(\".\").pop();\n  if (ext === \"xlsx\" || ext === \"xls\") return \"excel\";\n  if (ext === \"docx\") return \"word\";\n  if (ext === \"pdf\") return \"pdf\";\n  if (\n    ext === \"txt\" || ext === \"csv\" || ext === \"md\" || ext === \"json\" ||\n    ext === \"yaml\" || ext === \"yml\"\n  ) return \"text\";\n  return null;\n}\n\n/**\n * Get required packages for each file type\n */\nexport function getPackages(fileType: string): Record<string, string> {\n  const packages: Record<string, Record<string, string>> = {\n    excel: { openpyxl: \"openpyxl\" },\n    word: { docx: \"python-docx\" }, // Map docx import to python-docx package\n    pdf: { PyPDF2: \"PyPDF2\" },\n    text: {}, // No external packages needed for text files\n  };\n  return packages[fileType] || {};\n}\n\n/**\n * Get environment configuration\n */\nexport function getConfig() {\n  return {\n    rawFullRead: process.env.DOC_RAW_FULL_READ === \"true\",\n    pageSize: parseInt(process.env.DOC_PAGE_SIZE || \"100\", 10),\n    maxFileSize: parseInt(process.env.DOC_MAX_FILE_SIZE || \"50\", 10) * 1024 *\n      1024,\n  };\n}\n","#!/usr/bin/env node\n\nimport { Server } from \"@modelcontextprotocol/sdk/server/index.js\";\nimport { StdioServerTransport } from \"@modelcontextprotocol/sdk/server/stdio.js\";\nimport {\n  CallToolRequestSchema,\n  ListToolsRequestSchema,\n} from \"@modelcontextprotocol/sdk/types.js\";\nimport { z } from \"zod\";\nimport { runPythonFile } from \"./code-runner.js\";\nimport { detectFileType, getConfig, getPackages } from \"./utils.js\";\n\n// Tool schemas\nconst ReadDocumentSchema = z.object({\n  file_path: z.string().describe(\"Absolute path to the document file\"),\n  mode: z.enum([\"raw\", \"paginated\"]).optional().describe(\n    \"Read mode: 'raw' for full content, 'paginated' for chunked reading\",\n  ),\n  page: z.number().optional().describe(\n    \"Page number for paginated mode (1-based)\",\n  ),\n  page_size: z.number().optional().describe(\n    \"Items per page for paginated mode\",\n  ),\n  sheet_name: z.string().optional().describe(\"Sheet name for Excel files\"),\n});\n\nconst WriteDocumentSchema = z.object({\n  file_path: z.string().describe(\"Absolute path to save the document\"),\n  format: z.enum([\"excel\", \"word\", \"text\"]).describe(\"Document format\"),\n  data: z.any().describe(\"Document data structure\"),\n});\n\nconst GetDocumentInfoSchema = z.object({\n  file_path: z.string().describe(\"Absolute path to the document file\"),\n});\n\n// Server setup\nconst server = new Server(\n  {\n    name: \"docsmith-mcp\",\n    version: \"0.1.0\",\n  },\n  {\n    capabilities: {\n      tools: {},\n    },\n  },\n);\n\n// Output schemas (reusable)\nconst BaseOutputSchema = {\n  type: \"object\",\n  properties: {\n    success: { type: \"boolean\", description: \"Operation success status\" },\n    error: { type: \"string\", description: \"Error message if failed\" },\n  },\n} as const;\n\nconst PaginationSchema = {\n  current_page: { type: \"number\", description: \"Current page number\" },\n  page_size: { type: \"number\", description: \"Items per page\" },\n  total_pages: { type: \"number\", description: \"Total number of pages\" },\n  page: { type: \"number\", description: \"Current page number (alternative)\" },\n  has_more: { type: \"boolean\", description: \"Whether more pages exist\" },\n} as const;\n\nconst ExcelReadOutputSchema = {\n  type: \"object\",\n  properties: {\n    sheet_name: { type: \"string\", description: \"Active sheet name\" },\n    sheets: {\n      type: \"array\",\n      items: { type: \"string\" },\n      description: \"All sheet names\",\n    },\n    total_rows: { type: \"number\", description: \"Total rows in sheet\" },\n    total_cols: { type: \"number\", description: \"Total columns in sheet\" },\n    data: {\n      type: \"array\",\n      items: { type: \"array\", items: {} },\n      description: \"Sheet data as array of rows\",\n    },\n    ...PaginationSchema,\n  },\n} as const;\n\nconst WordReadOutputSchema = {\n  type: \"object\",\n  properties: {\n    paragraphs: {\n      type: \"array\",\n      items: { type: \"string\" },\n      description: \"Document paragraphs\",\n    },\n    tables: {\n      type: \"array\",\n      items: {\n        type: \"array\",\n        items: { type: \"array\", items: { type: \"string\" } },\n      },\n      description: \"Tables data\",\n    },\n    total_paragraphs: { type: \"number\", description: \"Total paragraph count\" },\n    total_tables: { type: \"number\", description: \"Total table count\" },\n    ...PaginationSchema,\n  },\n} as const;\n\nconst PDFReadOutputSchema = {\n  type: \"object\",\n  properties: {\n    total_pages: { type: \"number\", description: \"Total pages in PDF\" },\n    content: {\n      type: \"array\",\n      items: {\n        type: \"object\",\n        properties: {\n          page_number: { type: \"number\" },\n          text: { type: \"string\" },\n        },\n      },\n      description: \"Page content array\",\n    },\n    current_page_group: { type: \"number\" },\n    page_size: { type: \"number\" },\n  },\n} as const;\n\nconst TextReadOutputSchema = {\n  type: \"object\",\n  properties: {\n    ...BaseOutputSchema.properties,\n    content: { type: \"string\", description: \"Text content\" },\n    total_lines: { type: \"number\", description: \"Total line count\" },\n    encoding: { type: \"string\", description: \"File encoding\" },\n    ...PaginationSchema,\n  },\n} as const;\n\nconst CSVReadOutputSchema = {\n  type: \"object\",\n  properties: {\n    ...BaseOutputSchema.properties,\n    headers: {\n      type: \"array\",\n      items: { type: \"string\" },\n      description: \"CSV headers\",\n    },\n    data: {\n      type: \"array\",\n      items: { type: \"object\" },\n      description: \"Structured data as array of objects\",\n    },\n    total_rows: { type: \"number\", description: \"Total data rows\" },\n    encoding: { type: \"string\", description: \"File encoding\" },\n    ...PaginationSchema,\n  },\n} as const;\n\nconst JSONReadOutputSchema = {\n  type: \"object\",\n  properties: {\n    ...BaseOutputSchema.properties,\n    data: { type: \"object\", description: \"Parsed JSON data\" },\n    encoding: { type: \"string\", description: \"File encoding\" },\n  },\n} as const;\n\nconst WriteOutputSchema = {\n  type: \"object\",\n  properties: {\n    success: { type: \"boolean\", description: \"Write operation success\" },\n    file_path: { type: \"string\", description: \"Written file path\" },\n    message: { type: \"string\", description: \"Success message\" },\n    error: { type: \"string\", description: \"Error message if failed\" },\n  },\n} as const;\n\nconst ExcelInfoOutputSchema = {\n  type: \"object\",\n  properties: {\n    sheets: {\n      type: \"array\",\n      items: {\n        type: \"object\",\n        properties: {\n          name: { type: \"string\" },\n          rows: { type: \"number\" },\n          cols: { type: \"number\" },\n        },\n      },\n      description: \"Sheet information\",\n    },\n    file_size: { type: \"number\", description: \"File size in bytes\" },\n  },\n} as const;\n\nconst WordInfoOutputSchema = {\n  type: \"object\",\n  properties: {\n    paragraphs: { type: \"number\", description: \"Paragraph count\" },\n    tables: { type: \"number\", description: \"Table count\" },\n    file_size: { type: \"number\", description: \"File size in bytes\" },\n  },\n} as const;\n\nconst PDFInfoOutputSchema = {\n  type: \"object\",\n  properties: {\n    pages: { type: \"number\", description: \"Page count\" },\n    file_size: { type: \"number\", description: \"File size in bytes\" },\n    total_words: { type: \"number\", description: \"Total word count\" },\n  },\n} as const;\n\nconst TextInfoOutputSchema = {\n  type: \"object\",\n  properties: {\n    ...BaseOutputSchema.properties,\n    file_size: { type: \"number\", description: \"File size in bytes\" },\n    line_count: { type: \"number\", description: \"Line count\" },\n    encoding: { type: \"string\", description: \"File encoding\" },\n    file_type: { type: \"string\", description: \"File extension\" },\n    // CSV specific\n    headers: { type: \"array\", items: { type: \"string\" } },\n    total_rows: { type: \"number\" },\n    total_cols: { type: \"number\" },\n    // JSON specific\n    item_count: { type: \"number\" },\n    key_count: { type: \"number\" },\n  },\n} as const;\n\n// List available tools\nserver.setRequestHandler(ListToolsRequestSchema, async () => {\n  return {\n    tools: [\n      {\n        name: \"read_document\",\n        description:\n          \"Read document content (Excel, Word, PDF, TXT, CSV, Markdown, JSON, YAML). Supports raw full read or paginated mode.\",\n        inputSchema: {\n          type: \"object\",\n          properties: {\n            file_path: {\n              type: \"string\",\n              description: \"Absolute path to the document file\",\n            },\n            mode: {\n              type: \"string\",\n              enum: [\"raw\", \"paginated\"],\n              description: \"Read mode\",\n            },\n            page: {\n              type: \"number\",\n              description: \"Page number for paginated mode\",\n            },\n            page_size: { type: \"number\", description: \"Items per page\" },\n            sheet_name: {\n              type: \"string\",\n              description: \"Sheet name for Excel files\",\n            },\n          },\n          required: [\"file_path\"],\n        },\n        outputSchema: {\n          type: \"object\",\n          description:\n            \"Returns different structures based on file type: Excel (sheet data), Word (paragraphs/tables), PDF (page content), Text (plain text), CSV (structured rows), JSON (parsed object)\",\n          oneOf: [\n            ExcelReadOutputSchema,\n            WordReadOutputSchema,\n            PDFReadOutputSchema,\n            TextReadOutputSchema,\n            CSVReadOutputSchema,\n            JSONReadOutputSchema,\n          ],\n        },\n      },\n      {\n        name: \"write_document\",\n        description: \"Write document content (Excel, Word, Text)\",\n        inputSchema: {\n          type: \"object\",\n          properties: {\n            file_path: {\n              type: \"string\",\n              description: \"Absolute path to save the document\",\n            },\n            format: {\n              type: \"string\",\n              enum: [\"excel\", \"word\", \"text\"],\n              description: \"Document format\",\n            },\n            data: {\n              description:\n                \"Document data structure. Excel: array of rows [[cell1, cell2], ...]. Word: {paragraphs: string[], tables?: [[[cell]]]}. Text/CSV/JSON: string or object\",\n            },\n          },\n          required: [\"file_path\", \"format\", \"data\"],\n        },\n        outputSchema: WriteOutputSchema,\n      },\n      {\n        name: \"get_document_info\",\n        description:\n          \"Get document metadata (page count, sheet count, file size, etc.)\",\n        inputSchema: {\n          type: \"object\",\n          properties: {\n            file_path: {\n              type: \"string\",\n              description: \"Absolute path to the document file\",\n            },\n          },\n          required: [\"file_path\"],\n        },\n        outputSchema: {\n          type: \"object\",\n          description: \"Returns metadata based on file type\",\n          oneOf: [\n            ExcelInfoOutputSchema,\n            WordInfoOutputSchema,\n            PDFInfoOutputSchema,\n            TextInfoOutputSchema,\n          ],\n        },\n      },\n    ],\n  };\n});\n\n// Handle tool calls\nserver.setRequestHandler(CallToolRequestSchema, async (request) => {\n  const { name, arguments: args } = request.params;\n\n  try {\n    if (name === \"read_document\") {\n      const params = ReadDocumentSchema.parse(args);\n      const fileType = detectFileType(params.file_path);\n\n      if (!fileType) {\n        throw new Error(`Unsupported file type: ${params.file_path}`);\n      }\n\n      // Determine read mode\n      const config = getConfig();\n      const mode = params.mode || (config.rawFullRead ? \"raw\" : \"paginated\");\n      const page = mode === \"paginated\" ? (params.page || 1) : undefined;\n      const pageSize = params.page_size || config.pageSize;\n\n      let scriptName: string;\n      let scriptArgs: string[];\n\n      if (fileType === \"excel\") {\n        scriptName = \"excel_handler.py\";\n        scriptArgs = [\"read\", params.file_path];\n        if (params.sheet_name) scriptArgs.push(params.sheet_name);\n        if (page) {\n          scriptArgs.push(String(page));\n          scriptArgs.push(String(pageSize));\n        }\n      } else if (fileType === \"word\") {\n        scriptName = \"word_handler.py\";\n        scriptArgs = [\"read\", params.file_path];\n        if (page) {\n          scriptArgs.push(String(page));\n          scriptArgs.push(String(pageSize));\n        }\n      } else if (fileType === \"pdf\") {\n        scriptName = \"pdf_handler.py\";\n        scriptArgs = [\"read\", params.file_path];\n        if (page) {\n          scriptArgs.push(String(page));\n          scriptArgs.push(String(Math.min(pageSize, 10))); // PDF pages are larger\n        }\n      } else {\n        // text files\n        scriptName = \"text_handler.py\";\n        scriptArgs = [\"read\", params.file_path];\n        if (page) {\n          scriptArgs.push(String(page));\n          scriptArgs.push(String(pageSize));\n        }\n      }\n\n      const result = await runPythonFile(scriptName, {\n        args: scriptArgs,\n        packages: getPackages(fileType),\n        filePaths: [params.file_path],\n      });\n      return {\n        content: [{\n          type: \"text\",\n          text: JSON.stringify(result, null, 2),\n        }],\n        structuredContent: result,\n      };\n    }\n\n    if (name === \"write_document\") {\n      const params = WriteDocumentSchema.parse(args);\n\n      let scriptName: string;\n      let scriptArgs: string[];\n\n      if (params.format === \"excel\") {\n        scriptName = \"excel_handler.py\";\n        scriptArgs = [\"write\", params.file_path, JSON.stringify(params.data)];\n      } else if (params.format === \"word\") {\n        scriptName = \"word_handler.py\";\n        const paragraphs = params.data.paragraphs || [];\n        const tables = params.data.tables || null;\n        scriptArgs = [\"write\", params.file_path, JSON.stringify(paragraphs)];\n        if (tables) scriptArgs.push(JSON.stringify(tables));\n      } else if (params.format === \"text\") {\n        scriptName = \"text_handler.py\";\n        const content = typeof params.data === \"string\"\n          ? params.data\n          : JSON.stringify(params.data);\n        scriptArgs = [\"write\", params.file_path, content];\n      } else {\n        throw new Error(`Unsupported write format: ${params.format}`);\n      }\n\n      const result = await runPythonFile(scriptName, {\n        args: scriptArgs,\n        packages: getPackages(params.format),\n        filePaths: [params.file_path],\n      });\n      return {\n        content: [{\n          type: \"text\",\n          text: JSON.stringify(result, null, 2),\n        }],\n        structuredContent: result,\n      };\n    }\n\n    if (name === \"get_document_info\") {\n      const params = GetDocumentInfoSchema.parse(args);\n      const fileType = detectFileType(params.file_path);\n\n      if (!fileType) {\n        throw new Error(`Unsupported file type: ${params.file_path}`);\n      }\n\n      let scriptName: string;\n      let scriptArgs = [\"info\", params.file_path];\n\n      if (fileType === \"excel\") {\n        scriptName = \"excel_handler.py\";\n      } else if (fileType === \"word\") {\n        scriptName = \"word_handler.py\";\n      } else if (fileType === \"pdf\") {\n        scriptName = \"pdf_handler.py\";\n      } else {\n        scriptName = \"text_handler.py\";\n      }\n\n      const result = await runPythonFile(scriptName, {\n        args: scriptArgs,\n        packages: getPackages(fileType),\n        filePaths: [params.file_path],\n      });\n      return {\n        content: [{\n          type: \"text\",\n          text: JSON.stringify(result, null, 2),\n        }],\n        structuredContent: result,\n      };\n    }\n\n    throw new Error(`Unknown tool: ${name}`);\n  } catch (error) {\n    const errorMessage = error instanceof Error ? error.message : String(error);\n    return {\n      content: [{ type: \"text\", text: `Error: ${errorMessage}` }],\n      isError: true,\n    };\n  }\n});\n\n// Start server\nasync function main() {\n  const transport = new StdioServerTransport();\n  await server.connect(transport);\n  console.error(\"Docsmith MCP server running on stdio\");\n}\n\nmain().catch((error) => {\n  console.error(\"Server error:\", error);\n  process.exit(1);\n});\n"],"mappings":";;;;;;;;;;;AAQA,MAAM,aAAa,cAAc,OAAO,KAAK,IAAI;AACjD,MAAM,YAAY,QAAQ,WAAW;;;;;;;;AAuBrC,SAAS,qBACPA,UAC4C;CAC5C,MAAM,eAAe,QAAQ,SAAS;CAItC,MAAM,YAAY,QAAQ,aAAa;CACvC,MAAM,cAAc;AAEpB,QAAO;EAAE;EAAW;CAAa;AAClC;;;;;;;;AASD,eAAsB,cACpBC,YACAC,UAAgC,CAAE,GACpB;CACd,MAAM,EACJ,OAAO,CAAE,GACT,WAAW,CAAE,GACb,UAAU,UACV,YAAY,CAAE,GACf,GAAG;CAGJ,MAAM,WAAW,KAAK,WAAW,MAAM,SAAS,WAAW;CAC3D,MAAM,gBAAgB,aAAa,UAAU,QAAQ;CAGrD,MAAM,eAAe;;;;;eAKR,WAAW,OAAO,KAAK,UAAU,KAAK,CAAC;;;EAGpD,cAAc;;CAId,IAAI,YAAY,KAAK,WAAW,KAAK;AACrC,KAAI,UAAU,SAAS,GAAG;EACxB,MAAM,UAAU,qBAAqB,UAAU,GAAG;AAClD,cAAY,QAAQ;CACrB;CAID,MAAMC,eAA6B;EACjC;EACA,kBAAkB;EAClB,YAAY;CACb;CACD,MAAM,SAAS,MAAM,MAAM,aAAa,aAAa;CAGrD,MAAM,SAAS,OAAO,WAAW;CACjC,MAAM,UAAU,IAAI;CACpB,IAAI,SAAS;CACb,IAAI,SAAS;CACb,IAAI,QAAQ;AAEZ,KAAI;AACF,SAAO,MAAM;GACX,MAAM,EAAE,MAAM,OAAO,GAAG,MAAM,OAAO,MAAM;AAC3C,OAAI,KAAM;GAEV,MAAM,QAAQ,QAAQ,OAAO,OAAO,EAAE,QAAQ,KAAM,EAAC;AACrD,OAAI,MAAM,WAAW,YAAY,CAC/B,WAAU,MAAM,MAAM,EAAE;YACf,MAAM,WAAW,QAAQ,CAClC,UAAS;OAET,WAAU;EAEb;CACF,SAAQ,aAAa;AAEpB,SAAO,EAAE,OAAO,OAAO,YAAY,CAAE;CACtC;AAGD,KAAI,MACF,QAAO,EAAE,OAAO,MAAM,QAAQ,qBAAqB,GAAG,CAAC,MAAM,CAAE;CAIjE,MAAM,QAAQ,OAAO,MAAM,CAAC,MAAM,KAAK;CACvC,MAAM,WAAW,MAAM,MAAM,SAAS;AAEtC,KAAI;AACF,SAAO,KAAK,MAAM,SAAS;CAC5B,QAAO;AACN,SAAO;GAAE;GAAQ;EAAQ;CAC1B;AACF;;;;;;;;;;AChID,SAAgB,eACdC,UAC0C;CAC1C,MAAM,MAAM,SAAS,aAAa,CAAC,MAAM,IAAI,CAAC,KAAK;AACnD,KAAI,QAAQ,UAAU,QAAQ,MAAO,QAAO;AAC5C,KAAI,QAAQ,OAAQ,QAAO;AAC3B,KAAI,QAAQ,MAAO,QAAO;AAC1B,KACE,QAAQ,SAAS,QAAQ,SAAS,QAAQ,QAAQ,QAAQ,UAC1D,QAAQ,UAAU,QAAQ,MAC1B,QAAO;AACT,QAAO;AACR;;;;AAKD,SAAgB,YAAYC,UAA0C;CACpE,MAAMC,WAAmD;EACvD,OAAO,EAAE,UAAU,WAAY;EAC/B,MAAM,EAAE,MAAM,cAAe;EAC7B,KAAK,EAAE,QAAQ,SAAU;EACzB,MAAM,CAAE;CACT;AACD,QAAO,SAAS,aAAa,CAAE;AAChC;;;;AAKD,SAAgB,YAAY;AAC1B,QAAO;EACL,aAAa,QAAQ,IAAI,sBAAsB;EAC/C,UAAU,SAAS,QAAQ,IAAI,iBAAiB,OAAO,GAAG;EAC1D,aAAa,SAAS,QAAQ,IAAI,qBAAqB,MAAM,GAAG,GAAG,OACjE;CACH;AACF;;;;AC/BD,MAAM,qBAAqB,EAAE,OAAO;CAClC,WAAW,EAAE,QAAQ,CAAC,SAAS,qCAAqC;CACpE,MAAM,EAAE,KAAK,CAAC,OAAO,WAAY,EAAC,CAAC,UAAU,CAAC,SAC5C,qEACD;CACD,MAAM,EAAE,QAAQ,CAAC,UAAU,CAAC,SAC1B,2CACD;CACD,WAAW,EAAE,QAAQ,CAAC,UAAU,CAAC,SAC/B,oCACD;CACD,YAAY,EAAE,QAAQ,CAAC,UAAU,CAAC,SAAS,6BAA6B;AACzE,EAAC;AAEF,MAAM,sBAAsB,EAAE,OAAO;CACnC,WAAW,EAAE,QAAQ,CAAC,SAAS,qCAAqC;CACpE,QAAQ,EAAE,KAAK;EAAC;EAAS;EAAQ;CAAO,EAAC,CAAC,SAAS,kBAAkB;CACrE,MAAM,EAAE,KAAK,CAAC,SAAS,0BAA0B;AAClD,EAAC;AAEF,MAAM,wBAAwB,EAAE,OAAO,EACrC,WAAW,EAAE,QAAQ,CAAC,SAAS,qCAAqC,CACrE,EAAC;AAGF,MAAM,SAAS,IAAI,OACjB;CACE,MAAM;CACN,SAAS;AACV,GACD,EACE,cAAc,EACZ,OAAO,CAAE,EACV,EACF;AAIH,MAAM,mBAAmB;CACvB,MAAM;CACN,YAAY;EACV,SAAS;GAAE,MAAM;GAAW,aAAa;EAA4B;EACrE,OAAO;GAAE,MAAM;GAAU,aAAa;EAA2B;CAClE;AACF;AAED,MAAM,mBAAmB;CACvB,cAAc;EAAE,MAAM;EAAU,aAAa;CAAuB;CACpE,WAAW;EAAE,MAAM;EAAU,aAAa;CAAkB;CAC5D,aAAa;EAAE,MAAM;EAAU,aAAa;CAAyB;CACrE,MAAM;EAAE,MAAM;EAAU,aAAa;CAAqC;CAC1E,UAAU;EAAE,MAAM;EAAW,aAAa;CAA4B;AACvE;AAED,MAAM,wBAAwB;CAC5B,MAAM;CACN,YAAY;EACV,YAAY;GAAE,MAAM;GAAU,aAAa;EAAqB;EAChE,QAAQ;GACN,MAAM;GACN,OAAO,EAAE,MAAM,SAAU;GACzB,aAAa;EACd;EACD,YAAY;GAAE,MAAM;GAAU,aAAa;EAAuB;EAClE,YAAY;GAAE,MAAM;GAAU,aAAa;EAA0B;EACrE,MAAM;GACJ,MAAM;GACN,OAAO;IAAE,MAAM;IAAS,OAAO,CAAE;GAAE;GACnC,aAAa;EACd;EACD,GAAG;CACJ;AACF;AAED,MAAM,uBAAuB;CAC3B,MAAM;CACN,YAAY;EACV,YAAY;GACV,MAAM;GACN,OAAO,EAAE,MAAM,SAAU;GACzB,aAAa;EACd;EACD,QAAQ;GACN,MAAM;GACN,OAAO;IACL,MAAM;IACN,OAAO;KAAE,MAAM;KAAS,OAAO,EAAE,MAAM,SAAU;IAAE;GACpD;GACD,aAAa;EACd;EACD,kBAAkB;GAAE,MAAM;GAAU,aAAa;EAAyB;EAC1E,cAAc;GAAE,MAAM;GAAU,aAAa;EAAqB;EAClE,GAAG;CACJ;AACF;AAED,MAAM,sBAAsB;CAC1B,MAAM;CACN,YAAY;EACV,aAAa;GAAE,MAAM;GAAU,aAAa;EAAsB;EAClE,SAAS;GACP,MAAM;GACN,OAAO;IACL,MAAM;IACN,YAAY;KACV,aAAa,EAAE,MAAM,SAAU;KAC/B,MAAM,EAAE,MAAM,SAAU;IACzB;GACF;GACD,aAAa;EACd;EACD,oBAAoB,EAAE,MAAM,SAAU;EACtC,WAAW,EAAE,MAAM,SAAU;CAC9B;AACF;AAED,MAAM,uBAAuB;CAC3B,MAAM;CACN,YAAY;EACV,GAAG,iBAAiB;EACpB,SAAS;GAAE,MAAM;GAAU,aAAa;EAAgB;EACxD,aAAa;GAAE,MAAM;GAAU,aAAa;EAAoB;EAChE,UAAU;GAAE,MAAM;GAAU,aAAa;EAAiB;EAC1D,GAAG;CACJ;AACF;AAED,MAAM,sBAAsB;CAC1B,MAAM;CACN,YAAY;EACV,GAAG,iBAAiB;EACpB,SAAS;GACP,MAAM;GACN,OAAO,EAAE,MAAM,SAAU;GACzB,aAAa;EACd;EACD,MAAM;GACJ,MAAM;GACN,OAAO,EAAE,MAAM,SAAU;GACzB,aAAa;EACd;EACD,YAAY;GAAE,MAAM;GAAU,aAAa;EAAmB;EAC9D,UAAU;GAAE,MAAM;GAAU,aAAa;EAAiB;EAC1D,GAAG;CACJ;AACF;AAED,MAAM,uBAAuB;CAC3B,MAAM;CACN,YAAY;EACV,GAAG,iBAAiB;EACpB,MAAM;GAAE,MAAM;GAAU,aAAa;EAAoB;EACzD,UAAU;GAAE,MAAM;GAAU,aAAa;EAAiB;CAC3D;AACF;AAED,MAAM,oBAAoB;CACxB,MAAM;CACN,YAAY;EACV,SAAS;GAAE,MAAM;GAAW,aAAa;EAA2B;EACpE,WAAW;GAAE,MAAM;GAAU,aAAa;EAAqB;EAC/D,SAAS;GAAE,MAAM;GAAU,aAAa;EAAmB;EAC3D,OAAO;GAAE,MAAM;GAAU,aAAa;EAA2B;CAClE;AACF;AAED,MAAM,wBAAwB;CAC5B,MAAM;CACN,YAAY;EACV,QAAQ;GACN,MAAM;GACN,OAAO;IACL,MAAM;IACN,YAAY;KACV,MAAM,EAAE,MAAM,SAAU;KACxB,MAAM,EAAE,MAAM,SAAU;KACxB,MAAM,EAAE,MAAM,SAAU;IACzB;GACF;GACD,aAAa;EACd;EACD,WAAW;GAAE,MAAM;GAAU,aAAa;EAAsB;CACjE;AACF;AAED,MAAM,uBAAuB;CAC3B,MAAM;CACN,YAAY;EACV,YAAY;GAAE,MAAM;GAAU,aAAa;EAAmB;EAC9D,QAAQ;GAAE,MAAM;GAAU,aAAa;EAAe;EACtD,WAAW;GAAE,MAAM;GAAU,aAAa;EAAsB;CACjE;AACF;AAED,MAAM,sBAAsB;CAC1B,MAAM;CACN,YAAY;EACV,OAAO;GAAE,MAAM;GAAU,aAAa;EAAc;EACpD,WAAW;GAAE,MAAM;GAAU,aAAa;EAAsB;EAChE,aAAa;GAAE,MAAM;GAAU,aAAa;EAAoB;CACjE;AACF;AAED,MAAM,uBAAuB;CAC3B,MAAM;CACN,YAAY;EACV,GAAG,iBAAiB;EACpB,WAAW;GAAE,MAAM;GAAU,aAAa;EAAsB;EAChE,YAAY;GAAE,MAAM;GAAU,aAAa;EAAc;EACzD,UAAU;GAAE,MAAM;GAAU,aAAa;EAAiB;EAC1D,WAAW;GAAE,MAAM;GAAU,aAAa;EAAkB;EAE5D,SAAS;GAAE,MAAM;GAAS,OAAO,EAAE,MAAM,SAAU;EAAE;EACrD,YAAY,EAAE,MAAM,SAAU;EAC9B,YAAY,EAAE,MAAM,SAAU;EAE9B,YAAY,EAAE,MAAM,SAAU;EAC9B,WAAW,EAAE,MAAM,SAAU;CAC9B;AACF;AAGD,OAAO,kBAAkB,wBAAwB,YAAY;AAC3D,QAAO,EACL,OAAO;EACL;GACE,MAAM;GACN,aACE;GACF,aAAa;IACX,MAAM;IACN,YAAY;KACV,WAAW;MACT,MAAM;MACN,aAAa;KACd;KACD,MAAM;MACJ,MAAM;MACN,MAAM,CAAC,OAAO,WAAY;MAC1B,aAAa;KACd;KACD,MAAM;MACJ,MAAM;MACN,aAAa;KACd;KACD,WAAW;MAAE,MAAM;MAAU,aAAa;KAAkB;KAC5D,YAAY;MACV,MAAM;MACN,aAAa;KACd;IACF;IACD,UAAU,CAAC,WAAY;GACxB;GACD,cAAc;IACZ,MAAM;IACN,aACE;IACF,OAAO;KACL;KACA;KACA;KACA;KACA;KACA;IACD;GACF;EACF;EACD;GACE,MAAM;GACN,aAAa;GACb,aAAa;IACX,MAAM;IACN,YAAY;KACV,WAAW;MACT,MAAM;MACN,aAAa;KACd;KACD,QAAQ;MACN,MAAM;MACN,MAAM;OAAC;OAAS;OAAQ;MAAO;MAC/B,aAAa;KACd;KACD,MAAM,EACJ,aACE,0JACH;IACF;IACD,UAAU;KAAC;KAAa;KAAU;IAAO;GAC1C;GACD,cAAc;EACf;EACD;GACE,MAAM;GACN,aACE;GACF,aAAa;IACX,MAAM;IACN,YAAY,EACV,WAAW;KACT,MAAM;KACN,aAAa;IACd,EACF;IACD,UAAU,CAAC,WAAY;GACxB;GACD,cAAc;IACZ,MAAM;IACN,aAAa;IACb,OAAO;KACL;KACA;KACA;KACA;IACD;GACF;EACF;CACF,EACF;AACF,EAAC;AAGF,OAAO,kBAAkB,uBAAuB,OAAO,YAAY;CACjE,MAAM,EAAE,MAAM,WAAW,MAAM,GAAG,QAAQ;AAE1C,KAAI;AACF,MAAI,SAAS,iBAAiB;GAC5B,MAAM,SAAS,mBAAmB,MAAM,KAAK;GAC7C,MAAM,WAAW,eAAe,OAAO,UAAU;AAEjD,QAAK,SACH,OAAM,IAAI,OAAO,yBAAyB,OAAO,UAAU;GAI7D,MAAM,SAAS,WAAW;GAC1B,MAAM,OAAO,OAAO,SAAS,OAAO,cAAc,QAAQ;GAC1D,MAAM,OAAO,SAAS,cAAe,OAAO,QAAQ;GACpD,MAAM,WAAW,OAAO,aAAa,OAAO;GAE5C,IAAIC;GACJ,IAAIC;AAEJ,OAAI,aAAa,SAAS;AACxB,iBAAa;AACb,iBAAa,CAAC,QAAQ,OAAO,SAAU;AACvC,QAAI,OAAO,WAAY,YAAW,KAAK,OAAO,WAAW;AACzD,QAAI,MAAM;AACR,gBAAW,KAAK,OAAO,KAAK,CAAC;AAC7B,gBAAW,KAAK,OAAO,SAAS,CAAC;IAClC;GACF,WAAU,aAAa,QAAQ;AAC9B,iBAAa;AACb,iBAAa,CAAC,QAAQ,OAAO,SAAU;AACvC,QAAI,MAAM;AACR,gBAAW,KAAK,OAAO,KAAK,CAAC;AAC7B,gBAAW,KAAK,OAAO,SAAS,CAAC;IAClC;GACF,WAAU,aAAa,OAAO;AAC7B,iBAAa;AACb,iBAAa,CAAC,QAAQ,OAAO,SAAU;AACvC,QAAI,MAAM;AACR,gBAAW,KAAK,OAAO,KAAK,CAAC;AAC7B,gBAAW,KAAK,OAAO,KAAK,IAAI,UAAU,GAAG,CAAC,CAAC;IAChD;GACF,OAAM;AAEL,iBAAa;AACb,iBAAa,CAAC,QAAQ,OAAO,SAAU;AACvC,QAAI,MAAM;AACR,gBAAW,KAAK,OAAO,KAAK,CAAC;AAC7B,gBAAW,KAAK,OAAO,SAAS,CAAC;IAClC;GACF;GAED,MAAM,SAAS,MAAM,cAAc,YAAY;IAC7C,MAAM;IACN,UAAU,YAAY,SAAS;IAC/B,WAAW,CAAC,OAAO,SAAU;GAC9B,EAAC;AACF,UAAO;IACL,SAAS,CAAC;KACR,MAAM;KACN,MAAM,KAAK,UAAU,QAAQ,MAAM,EAAE;IACtC,CAAC;IACF,mBAAmB;GACpB;EACF;AAED,MAAI,SAAS,kBAAkB;GAC7B,MAAM,SAAS,oBAAoB,MAAM,KAAK;GAE9C,IAAID;GACJ,IAAIC;AAEJ,OAAI,OAAO,WAAW,SAAS;AAC7B,iBAAa;AACb,iBAAa;KAAC;KAAS,OAAO;KAAW,KAAK,UAAU,OAAO,KAAK;IAAC;GACtE,WAAU,OAAO,WAAW,QAAQ;AACnC,iBAAa;IACb,MAAM,aAAa,OAAO,KAAK,cAAc,CAAE;IAC/C,MAAM,SAAS,OAAO,KAAK,UAAU;AACrC,iBAAa;KAAC;KAAS,OAAO;KAAW,KAAK,UAAU,WAAW;IAAC;AACpE,QAAI,OAAQ,YAAW,KAAK,KAAK,UAAU,OAAO,CAAC;GACpD,WAAU,OAAO,WAAW,QAAQ;AACnC,iBAAa;IACb,MAAM,iBAAiB,OAAO,SAAS,WACnC,OAAO,OACP,KAAK,UAAU,OAAO,KAAK;AAC/B,iBAAa;KAAC;KAAS,OAAO;KAAW;IAAQ;GAClD,MACC,OAAM,IAAI,OAAO,4BAA4B,OAAO,OAAO;GAG7D,MAAM,SAAS,MAAM,cAAc,YAAY;IAC7C,MAAM;IACN,UAAU,YAAY,OAAO,OAAO;IACpC,WAAW,CAAC,OAAO,SAAU;GAC9B,EAAC;AACF,UAAO;IACL,SAAS,CAAC;KACR,MAAM;KACN,MAAM,KAAK,UAAU,QAAQ,MAAM,EAAE;IACtC,CAAC;IACF,mBAAmB;GACpB;EACF;AAED,MAAI,SAAS,qBAAqB;GAChC,MAAM,SAAS,sBAAsB,MAAM,KAAK;GAChD,MAAM,WAAW,eAAe,OAAO,UAAU;AAEjD,QAAK,SACH,OAAM,IAAI,OAAO,yBAAyB,OAAO,UAAU;GAG7D,IAAID;GACJ,IAAI,aAAa,CAAC,QAAQ,OAAO,SAAU;AAE3C,OAAI,aAAa,QACf,cAAa;YACJ,aAAa,OACtB,cAAa;YACJ,aAAa,MACtB,cAAa;OAEb,cAAa;GAGf,MAAM,SAAS,MAAM,cAAc,YAAY;IAC7C,MAAM;IACN,UAAU,YAAY,SAAS;IAC/B,WAAW,CAAC,OAAO,SAAU;GAC9B,EAAC;AACF,UAAO;IACL,SAAS,CAAC;KACR,MAAM;KACN,MAAM,KAAK,UAAU,QAAQ,MAAM,EAAE;IACtC,CAAC;IACF,mBAAmB;GACpB;EACF;AAED,QAAM,IAAI,OAAO,gBAAgB,KAAK;CACvC,SAAQ,OAAO;EACd,MAAM,eAAe,iBAAiB,QAAQ,MAAM,UAAU,OAAO,MAAM;AAC3E,SAAO;GACL,SAAS,CAAC;IAAE,MAAM;IAAQ,OAAO,SAAS,aAAa;GAAG,CAAC;GAC3D,SAAS;EACV;CACF;AACF,EAAC;AAGF,eAAe,OAAO;CACpB,MAAM,YAAY,IAAI;AACtB,OAAM,OAAO,QAAQ,UAAU;AAC/B,SAAQ,MAAM,uCAAuC;AACtD;AAED,MAAM,CAAC,MAAM,CAAC,UAAU;AACtB,SAAQ,MAAM,iBAAiB,MAAM;AACrC,SAAQ,KAAK,EAAE;AAChB,EAAC"}

package/dist/python/excel_handler.py

@@ -0,0 +1,97 @@
+"""
+Excel document handler - read/write Excel files
+"""
+import json
+import sys
+from pathlib import Path
+
+def read_excel(file_path: str, sheet_name: str = None, page: int = None, page_size: int = 100):
+    """Read Excel file with optional pagination"""
+    import openpyxl
+    
+    wb = openpyxl.load_workbook(file_path, data_only=True)
+    
+    if sheet_name is None:
+        sheet_name = wb.sheetnames[0]
+    
+    ws = wb[sheet_name]
+    
+    # Get all data
+    data = []
+    for row in ws.iter_rows(values_only=True):
+        data.append(row)
+    
+    # Handle pagination
+    if page is not None:
+        start = (page - 1) * page_size
+        end = start + page_size
+        data = data[start:end]
+        total_pages = (len(data) + page_size - 1) // page_size if data else 1
+    else:
+        total_pages = 1
+    
+    return {
+        "sheet_name": sheet_name,
+        "sheets": wb.sheetnames,
+        "total_rows": ws.max_row,
+        "total_cols": ws.max_column,
+        "current_page": page,
+        "page_size": page_size if page else None,
+        "total_pages": total_pages,
+        "data": data
+    }
+
+def get_excel_info(file_path: str):
+    """Get Excel file metadata"""
+    import openpyxl
+    
+    wb = openpyxl.load_workbook(file_path, data_only=True)
+    info = {
+        "sheets": [],
+        "file_size": Path(file_path).stat().st_size
+    }
+    
+    for sheet_name in wb.sheetnames:
+        ws = wb[sheet_name]
+        info["sheets"].append({
+            "name": sheet_name,
+            "rows": ws.max_row,
+            "cols": ws.max_column
+        })
+    
+    return info
+
+def write_excel(file_path: str, data: list, sheet_name: str = "Sheet1"):
+    """Write data to Excel file"""
+    import openpyxl
+    
+    wb = openpyxl.Workbook()
+    ws = wb.active
+    ws.title = sheet_name
+    
+    for row in data:
+        ws.append(row)
+    
+    wb.save(file_path)
+    return {"success": True, "file_path": file_path}
+
+if __name__ == "__main__":
+    command = sys.argv[1]
+    file_path = sys.argv[2]
+    
+    if command == "read":
+        sheet = sys.argv[3] if len(sys.argv) > 3 else None
+        page = int(sys.argv[4]) if len(sys.argv) > 4 else None
+        page_size = int(sys.argv[5]) if len(sys.argv) > 5 else 100
+        result = read_excel(file_path, sheet, page, page_size)
+    elif command == "info":
+        result = get_excel_info(file_path)
+    elif command == "write":
+        # Data passed as JSON string
+        data = json.loads(sys.argv[3])
+        sheet = sys.argv[4] if len(sys.argv) > 4 else "Sheet1"
+        result = write_excel(file_path, data, sheet)
+    else:
+        result = {"error": f"Unknown command: {command}"}
+    
+    print(json.dumps(result, default=str))

package/dist/python/pdf_handler.py

@@ -0,0 +1,81 @@
+"""
+PDF document handler - read PDF files using PyPDF2
+"""
+import json
+import sys
+from pathlib import Path
+
+def read_pdf(file_path: str, page: int = None, page_size: int = 100):
+    """Read PDF with optional pagination by pages"""
+    from PyPDF2 import PdfReader
+    
+    reader = PdfReader(file_path)
+    total_pages = len(reader.pages)
+    
+    # Handle pagination
+    if page is not None:
+        start_page = (page - 1) * page_size
+        end_page = min(start_page + page_size, total_pages)
+        pages_to_read = range(start_page, end_page)
+        current_page = page
+        total_page_groups = (total_pages + page_size - 1) // page_size
+    else:
+        pages_to_read = range(total_pages)
+        current_page = None
+        total_page_groups = 1
+    
+    content = []
+    for i in pages_to_read:
+        page_obj = reader.pages[i]
+        text = page_obj.extract_text()
+        content.append({
+            "page_number": i + 1,
+            "text": text or "",
+            "words": len(text.split()) if text else 0
+        })
+    
+    return {
+        "total_pages": total_pages,
+        "current_page_group": current_page,
+        "page_size": page_size if page else None,
+        "total_page_groups": total_page_groups,
+        "content": content
+    }
+
+def get_pdf_info(file_path: str):
+    """Get PDF metadata"""
+    from PyPDF2 import PdfReader
+    
+    reader = PdfReader(file_path)
+    info = {
+        "pages": len(reader.pages),
+        "file_size": Path(file_path).stat().st_size
+    }
+    
+    # Try to get PDF metadata
+    if reader.metadata:
+        info["metadata"] = {k: str(v) for k, v in reader.metadata.items()}
+    
+    # Count total words
+    total_words = 0
+    for page in reader.pages:
+        text = page.extract_text() or ""
+        total_words += len(text.split())
+    info["total_words"] = total_words
+    
+    return info
+
+if __name__ == "__main__":
+    command = sys.argv[1]
+    file_path = sys.argv[2]
+    
+    if command == "read":
+        page = int(sys.argv[3]) if len(sys.argv) > 3 else None
+        page_size = int(sys.argv[4]) if len(sys.argv) > 4 else 10
+        result = read_pdf(file_path, page, page_size)
+    elif command == "info":
+        result = get_pdf_info(file_path)
+    else:
+        result = {"error": f"Unknown command: {command}"}
+    
+    print(json.dumps(result, default=str))

package/dist/python/text_handler.py

@@ -0,0 +1,331 @@
+#!/usr/bin/env python3
+"""
+Text file handler - supports .txt, .csv, .md, .json, .yaml, .yml
+Provides structured parsing for CSV and JSON files
+"""
+
+import sys
+import json
+import os
+import csv
+from io import StringIO
+
+
+def detect_file_type(file_path):
+    """Detect file type from extension."""
+    ext = file_path.lower().split('.')[-1] if '.' in file_path else ''
+    return ext
+
+
+def read_text(file_path, page=None, page_size=None):
+    """Read text file with optional pagination."""
+    try:
+        # Detect encoding
+        encodings = ['utf-8', 'utf-8-sig', 'gbk', 'gb2312', 'latin-1']
+        content = None
+        used_encoding = None
+        
+        for encoding in encodings:
+            try:
+                with open(file_path, 'r', encoding=encoding) as f:
+                    content = f.read()
+                used_encoding = encoding
+                break
+            except UnicodeDecodeError:
+                continue
+        
+        if content is None:
+            raise Exception("Could not decode file with any supported encoding")
+        
+        lines = content.split('\n')
+        total_lines = len(lines)
+        
+        # Pagination
+        if page is not None and page_size is not None:
+            start = (page - 1) * page_size
+            end = start + page_size
+            paginated_lines = lines[start:end]
+            has_more = end < total_lines
+            
+            return {
+                "success": True,
+                "content": '\n'.join(paginated_lines),
+                "total_lines": total_lines,
+                "page": page,
+                "page_size": page_size,
+                "has_more": has_more,
+                "encoding": used_encoding
+            }
+        else:
+            return {
+                "success": True,
+                "content": content,
+                "total_lines": total_lines,
+                "encoding": used_encoding
+            }
+    except Exception as e:
+        return {"success": False, "error": str(e)}
+
+
+def read_csv(file_path, page=None, page_size=None):
+    """Read CSV file and return structured data."""
+    try:
+        encodings = ['utf-8', 'utf-8-sig', 'gbk', 'gb2312', 'latin-1']
+        content = None
+        used_encoding = None
+        
+        for encoding in encodings:
+            try:
+                with open(file_path, 'r', encoding=encoding) as f:
+                    content = f.read()
+                used_encoding = encoding
+                break
+            except UnicodeDecodeError:
+                continue
+        
+        if content is None:
+            raise Exception("Could not decode file with any supported encoding")
+        
+        # Parse CSV
+        reader = csv.reader(StringIO(content))
+        rows = list(reader)
+        
+        if not rows:
+            return {
+                "success": True,
+                "headers": [],
+                "data": [],
+                "total_rows": 0,
+                "encoding": used_encoding
+            }
+        
+        headers = rows[0]
+        data_rows = rows[1:]
+        total_rows = len(data_rows)
+        
+        # Convert to list of dicts
+        structured_data = []
+        for row in data_rows:
+            row_dict = {}
+            for i, header in enumerate(headers):
+                row_dict[header] = row[i] if i < len(row) else ""
+            structured_data.append(row_dict)
+        
+        # Pagination
+        if page is not None and page_size is not None:
+            start = (page - 1) * page_size
+            end = start + page_size
+            paginated_data = structured_data[start:end]
+            has_more = end < total_rows
+            
+            return {
+                "success": True,
+                "headers": headers,
+                "data": paginated_data,
+                "total_rows": total_rows,
+                "page": page,
+                "page_size": page_size,
+                "has_more": has_more,
+                "encoding": used_encoding
+            }
+        else:
+            return {
+                "success": True,
+                "headers": headers,
+                "data": structured_data,
+                "total_rows": total_rows,
+                "encoding": used_encoding
+            }
+    except Exception as e:
+        return {"success": False, "error": str(e)}
+
+
+def read_json(file_path):
+    """Read JSON file and return parsed object."""
+    try:
+        encodings = ['utf-8', 'utf-8-sig', 'gbk', 'gb2312', 'latin-1']
+        content = None
+        used_encoding = None
+        
+        for encoding in encodings:
+            try:
+                with open(file_path, 'r', encoding=encoding) as f:
+                    content = f.read()
+                used_encoding = encoding
+                break
+            except UnicodeDecodeError:
+                continue
+        
+        if content is None:
+            raise Exception("Could not decode file with any supported encoding")
+        
+        parsed = json.loads(content)
+        
+        return {
+            "success": True,
+            "data": parsed,
+            "encoding": used_encoding
+        }
+    except json.JSONDecodeError as e:
+        return {"success": False, "error": f"Invalid JSON: {str(e)}"}
+    except Exception as e:
+        return {"success": False, "error": str(e)}
+
+
+def write_text(file_path, content):
+    """Write content to text file."""
+    try:
+        with open(file_path, 'w', encoding='utf-8') as f:
+            f.write(content)
+        return {"success": True, "message": "File written successfully"}
+    except Exception as e:
+        return {"success": False, "error": str(e)}
+
+
+def write_csv(file_path, data):
+    """Write data to CSV file."""
+    try:
+        if isinstance(data, str):
+            data = json.loads(data)
+        
+        with open(file_path, 'w', encoding='utf-8', newline='') as f:
+            if data and len(data) > 0:
+                writer = csv.DictWriter(f, fieldnames=data[0].keys())
+                writer.writeheader()
+                writer.writerows(data)
+        return {"success": True, "message": "CSV file written successfully"}
+    except Exception as e:
+        return {"success": False, "error": str(e)}
+
+
+def write_json(file_path, data):
+    """Write data to JSON file."""
+    try:
+        if isinstance(data, str):
+            data = json.loads(data)
+        
+        with open(file_path, 'w', encoding='utf-8') as f:
+            json.dump(data, f, ensure_ascii=False, indent=2)
+        return {"success": True, "message": "JSON file written successfully"}
+    except Exception as e:
+        return {"success": False, "error": str(e)}
+
+
+def get_info(file_path):
+    """Get text file metadata."""
+    try:
+        stat = os.stat(file_path)
+        file_type = detect_file_type(file_path)
+        
+        # Try to detect encoding and count lines
+        encodings = ['utf-8', 'utf-8-sig', 'gbk', 'gb2312', 'latin-1']
+        line_count = 0
+        encoding = None
+        
+        for enc in encodings:
+            try:
+                with open(file_path, 'r', encoding=enc) as f:
+                    content = f.read()
+                    line_count = len(content.split('\n'))
+                encoding = enc
+                break
+            except UnicodeDecodeError:
+                continue
+        
+        result = {
+            "success": True,
+            "file_size": stat.st_size,
+            "line_count": line_count,
+            "encoding": encoding or "unknown",
+            "file_type": file_type
+        }
+        
+        # Add type-specific info
+        if file_type == 'csv':
+            try:
+                with open(file_path, 'r', encoding=encoding or 'utf-8') as f:
+                    reader = csv.reader(f)
+                    rows = list(reader)
+                    if rows:
+                        result['headers'] = rows[0]
+                        result['total_rows'] = len(rows) - 1
+                        result['total_cols'] = len(rows[0])
+            except:
+                pass
+        elif file_type == 'json':
+            try:
+                with open(file_path, 'r', encoding=encoding or 'utf-8') as f:
+                    data = json.load(f)
+                    if isinstance(data, list):
+                        result['item_count'] = len(data)
+                    elif isinstance(data, dict):
+                        result['key_count'] = len(data.keys())
+            except:
+                pass
+        
+        return result
+    except Exception as e:
+        return {"success": False, "error": str(e)}
+
+
+def main():
+    if len(sys.argv) < 2:
+        print(json.dumps({"success": False, "error": "No command specified"}))
+        return
+    
+    command = sys.argv[1]
+    
+    if command == "read":
+        if len(sys.argv) < 3:
+            print(json.dumps({"success": False, "error": "No file path specified"}))
+            return
+        
+        file_path = sys.argv[2]
+        page = int(sys.argv[3]) if len(sys.argv) > 3 else None
+        page_size = int(sys.argv[4]) if len(sys.argv) > 4 else None
+        
+        file_type = detect_file_type(file_path)
+        
+        if file_type == 'csv':
+            result = read_csv(file_path, page, page_size)
+        elif file_type == 'json':
+            result = read_json(file_path)
+        else:
+            result = read_text(file_path, page, page_size)
+        
+        print(json.dumps(result))
+    
+    elif command == "write":
+        if len(sys.argv) < 4:
+            print(json.dumps({"success": False, "error": "Insufficient arguments"}))
+            return
+        
+        file_path = sys.argv[2]
+        content = sys.argv[3]
+        
+        file_type = detect_file_type(file_path)
+        
+        if file_type == 'csv':
+            result = write_csv(file_path, content)
+        elif file_type == 'json':
+            result = write_json(file_path, content)
+        else:
+            result = write_text(file_path, content)
+        
+        print(json.dumps(result))
+    
+    elif command == "info":
+        if len(sys.argv) < 3:
+            print(json.dumps({"success": False, "error": "No file path specified"}))
+            return
+        
+        file_path = sys.argv[2]
+        result = get_info(file_path)
+        print(json.dumps(result))
+    
+    else:
+        print(json.dumps({"success": False, "error": f"Unknown command: {command}"}))
+
+
+if __name__ == "__main__":
+    main()

package/dist/python/word_handler.py

@@ -0,0 +1,98 @@
+"""
+Word document handler - read/write DOCX files
+"""
+import json
+import sys
+from pathlib import Path
+
+def read_word(file_path: str, page: int = None, page_size: int = 100):
+    """Read Word document with optional pagination by paragraphs"""
+    from docx import Document
+    
+    doc = Document(file_path)
+    
+    # Extract paragraphs
+    paragraphs = [p.text for p in doc.paragraphs if p.text.strip()]
+    
+    # Extract tables
+    tables = []
+    for table in doc.tables:
+        table_data = []
+        for row in table.rows:
+            row_data = [cell.text for cell in row.cells]
+            table_data.append(row_data)
+        tables.append(table_data)
+    
+    # Handle pagination for paragraphs
+    if page is not None:
+        start = (page - 1) * page_size
+        end = start + page_size
+        paragraphs = paragraphs[start:end]
+        total_pages = (len(doc.paragraphs) + page_size - 1) // page_size
+    else:
+        total_pages = 1
+    
+    return {
+        "paragraphs": paragraphs,
+        "tables": tables,
+        "total_paragraphs": len(doc.paragraphs),
+        "total_tables": len(doc.tables),
+        "current_page": page,
+        "page_size": page_size if page else None,
+        "total_pages": total_pages
+    }
+
+def get_word_info(file_path: str):
+    """Get Word document metadata"""
+    from docx import Document
+    
+    doc = Document(file_path)
+    
+    # Count non-empty paragraphs
+    para_count = sum(1 for p in doc.paragraphs if p.text.strip())
+    
+    return {
+        "paragraphs": para_count,
+        "tables": len(doc.tables),
+        "file_size": Path(file_path).stat().st_size
+    }
+
+def write_word(file_path: str, paragraphs: list, tables: list = None):
+    """Write data to Word document"""
+    from docx import Document
+    
+    doc = Document()
+    
+    # Add paragraphs
+    for text in paragraphs:
+        doc.add_paragraph(text)
+    
+    # Add tables if provided
+    if tables:
+        for table_data in tables:
+            table = doc.add_table(rows=len(table_data), cols=len(table_data[0]) if table_data else 1)
+            for i, row_data in enumerate(table_data):
+                for j, cell_text in enumerate(row_data):
+                    table.rows[i].cells[j].text = str(cell_text)
+    
+    doc.save(file_path)
+    return {"success": True, "file_path": file_path}
+
+if __name__ == "__main__":
+    command = sys.argv[1]
+    file_path = sys.argv[2]
+    
+    if command == "read":
+        page = int(sys.argv[3]) if len(sys.argv) > 3 else None
+        page_size = int(sys.argv[4]) if len(sys.argv) > 4 else 100
+        result = read_word(file_path, page, page_size)
+    elif command == "info":
+        result = get_word_info(file_path)
+    elif command == "write":
+        paragraphs = json.loads(sys.argv[3])
+        tables = json.loads(sys.argv[4]) if len(sys.argv) > 4 else None
+        result = write_word(file_path, paragraphs, tables)
+    else:
+        result = {"error": f"Unknown command: {command}"}
+    
+    print(json.dumps(result, default=str))