merge

README.md

@@ -13,66 +13,51 @@ tags:
   - mcp-server-track
 ---
 
-# Document Extraction Tool
+# Document Extraction Tool - Simplified Version
 
-This tool extracts text from PDF and DOCX files and converts it to Markdown format. It uses the Docling library for powerful document content extraction, including text, tables, and images.
+A streamlined tool that extracts text from PDF and DOCX files and converts it to Markdown format. The extractor is initialized at startup and ready to process documents on demand.
 
 ## Features
 
-- Support for PDF and DOCX document formats
-- Extraction of text content from documents
-- Preservation of document format and structure
-- Support for table and image extraction
-- Conversion of extracted content to Markdown format
-- Support for downloading extraction results
-- **Enhanced Error Handling** - Automatic fallback for problematic documents
-- **Font Issue Resolution** - Special handling for PDFs with font parsing problems
-- **MCP Integration** - Compatible with Claude Desktop via Model Context Protocol
+- **Fast startup** - Extractor pre-initialized and ready to use
+- **PDF & DOCX support** - Extract text from common document formats  
+- **Markdown output** - Clean, structured markdown format
+- **Enhanced extraction** - Uses Docling when available, PyPDF2 as fallback
+- **Error handling** - Graceful handling of corrupted or problematic files
+- **Simple interface** - Clean, easy-to-use web interface
 
-## Installation and Setup
+## Quick Start
 
 ```bash
 # Install dependencies
 pip install -r requirements.txt
 
-# Run the application
+# Run the application  
 python app.py
 ```
 
-The application will be available at:
-- Web Interface: `http://localhost:7860`
-- MCP Server: `http://localhost:7860/gradio_api/mcp/sse`
+Access the tool at: `http://localhost:7860`
 
-
-## Usage Instructions
+## Usage
 
 1. Upload a PDF or DOCX document
-2. Click the "Extract Text" button
+2. Click "Extract Text" 
 3. View the extracted Markdown content
-4. Download the extraction results
-
-### Troubleshooting
-
-For detailed troubleshooting information, see [TROUBLESHOOTING.md](TROUBLESHOOTING.md).
-
-**Common Issues:**
+4. Download the results if needed
 
-- **Font Parsing Errors**: The app automatically attempts fallback conversion for PDFs with unsupported fonts
-- **Document Corruption**: Ensure files are complete and not corrupted
-- **Password Protection**: Remove password protection before uploading
-- **Large Files**: Processing time increases with file size - please be patient
+## Technology
 
-**Error Recovery Features:**
-- Automatic fallback processing for font-related issues
-- OCR backup for problematic text extraction
-- Conservative processing mode for complex documents
-- User-friendly error messages with specific guidance
+- **Gradio** - Web interface
+- **Docling** - Advanced document extraction (optional)
+- **PyPDF2** - PDF processing fallback
+- **python-docx** - DOCX processing
 
-## Technology Stack
+## Architecture
 
-- Gradio: For creating the web interface
-- Docling: For document content extraction
-- Python 3.7+
+The tool uses a singleton pattern with a pre-initialized extractor:
+- Faster response times (no initialization delay)
+- Automatic fallback between extraction methods
+- Enhanced error handling for edge cases
 
 ## License
 

extractor.py

@@ -1,242 +0,0 @@
-#!/usr/bin/env python3
-"""
-简化的文档提取器 - 专为Hugging Face Spaces优化
-支持PDF和DOCX文件转换为Markdown格式
-"""
-
-import logging
-import os
-import io
-import sys
-from pathlib import Path
-from typing import Union, Optional
-
-# 配置日志
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-# 尝试导入依赖库
-try:
-    import PyPDF2
-
-    PDF_AVAILABLE = True
-except ImportError:
-    PDF_AVAILABLE = False
-    logger.warning("PyPDF2 not available - PDF processing disabled")
-
-try:
-    import docx
-
-    DOCX_AVAILABLE = True
-except ImportError:
-    DOCX_AVAILABLE = False
-    logger.warning("python-docx not available - DOCX processing disabled")
-
-
-class DocumentExtractor:
-    """简化的文档提取器类"""
-
-    def __init__(self):
-        """初始化提取器"""
-        self.supported_formats = []
-
-        if PDF_AVAILABLE:
-            self.supported_formats.append(".pdf")
-        if DOCX_AVAILABLE:
-            self.supported_formats.append(".docx")
-
-        if not self.supported_formats:
-            raise RuntimeError("没有可用的文档处理库。请安装PyPDF2和python-docx。")
-
-        logger.info(f"文档提取器初始化完成，支持格式: {self.supported_formats}")
-
-    def validate_document(self, file_path: Union[str, Path]) -> bool:
-        """
-        验证文档是否可以处理
-
-        Args:
-            file_path: 文件路径
-
-        Returns:
-            bool: 如果文档有效返回True
-        """
-        try:
-            path = Path(file_path)
-
-            # 检查文件是否存在
-            if not path.exists():
-                logger.error(f"文件不存在: {file_path}")
-                return False
-
-            # 检查文件扩展名
-            file_ext = path.suffix.lower()
-            if file_ext not in self.supported_formats:
-                logger.error(f"不支持的文件格式: {file_ext}")
-                return False
-
-            # 检查文件大小
-            file_size = path.stat().st_size
-            if file_size == 0:
-                logger.error("文件为空")
-                return False
-
-            if file_size > 100 * 1024 * 1024:  # 100MB限制
-                logger.warning(
-                    f"文件较大 ({file_size / 1024 / 1024:.2f} MB)，处理可能需要较长时间"
-                )
-
-            return True
-
-        except Exception as e:
-            logger.error(f"文件验证失败: {str(e)}")
-            return False
-
-    def extract_pdf_text(self, file_path: Union[str, Path]) -> str:
-        """
-        从PDF文件提取文本
-
-        Args:
-            file_path: PDF文件路径
-
-        Returns:
-            str: 提取的文本内容
-        """
-        if not PDF_AVAILABLE:
-            raise RuntimeError("PDF处理不可用 - 请安装PyPDF2")
-
-        try:
-            with open(file_path, "rb") as file:
-                pdf_reader = PyPDF2.PdfReader(file)
-                text_content = []
-
-                for page_num, page in enumerate(pdf_reader.pages):
-                    try:
-                        page_text = page.extract_text()
-                        if page_text.strip():
-                            text_content.append(
-                                f"## 第 {page_num + 1} 页\n\n{page_text}\n"
-                            )
-                    except Exception as e:
-                        logger.warning(f"无法提取第 {page_num + 1} 页内容: {str(e)}")
-                        continue
-
-                if not text_content:
-                    return "# PDF文档\n\n无法从此PDF文件中提取文本内容。"
-
-                return "# PDF文档\n\n" + "\n".join(text_content)
-
-        except Exception as e:
-            logger.error(f"PDF提取失败: {str(e)}")
-            return f"# PDF提取错误\n\n提取过程中出现错误: {str(e)}"
-
-    def extract_docx_text(self, file_path: Union[str, Path]) -> str:
-        """
-        从DOCX文件提取文本
-
-        Args:
-            file_path: DOCX文件路径
-
-        Returns:
-            str: 提取的文本内容
-        """
-        if not DOCX_AVAILABLE:
-            raise RuntimeError("DOCX处理不可用 - 请安装python-docx")
-
-        try:
-            doc = docx.Document(file_path)
-            text_content = []
-
-            for paragraph in doc.paragraphs:
-                if paragraph.text.strip():
-                    # 简单的格式检测
-                    text = paragraph.text.strip()
-
-                    # 检测标题（简单规则）
-                    if (
-                        len(text) < 100
-                        and not text.endswith(".")
-                        and not text.endswith("。")
-                    ):
-                        text_content.append(f"## {text}\n")
-                    else:
-                        text_content.append(f"{text}\n")
-
-            # 处理表格
-            for table in doc.tables:
-                text_content.append("\n### 表格\n")
-                for row in table.rows:
-                    row_text = " | ".join([cell.text.strip() for cell in row.cells])
-                    if row_text.strip():
-                        text_content.append(f"| {row_text} |")
-                text_content.append("\n")
-
-            if not text_content:
-                return "# Word文档\n\n无法从此DOCX文件中提取文本内容。"
-
-            return "# Word文档\n\n" + "\n".join(text_content)
-
-        except Exception as e:
-            logger.error(f"DOCX提取失败: {str(e)}")
-            return f"# DOCX提取错误\n\n提取过程中出现错误: {str(e)}"
-
-    def extract(self, file_path: Union[str, Path]) -> str:
-        """
-        提取文档内容并转换为Markdown格式
-
-        Args:
-            file_path: 文档文件路径
-
-        Returns:
-            str: Markdown格式的文档内容
-        """
-        logger.info(f"开始提取文档: {file_path}")
-
-        # 验证文档
-        if not self.validate_document(file_path):
-            raise ValueError(f"文档验证失败: {file_path}")
-
-        # 确定文件类型并提取
-        file_ext = Path(file_path).suffix.lower()
-
-        try:
-            if file_ext == ".pdf":
-                content = self.extract_pdf_text(file_path)
-            elif file_ext == ".docx":
-                content = self.extract_docx_text(file_path)
-            else:
-                raise ValueError(f"不支持的文件格式: {file_ext}")
-
-            logger.info(f"文档提取完成，内容长度: {len(content)} 字符")
-            return content
-
-        except Exception as e:
-            logger.error(f"文档提取失败: {str(e)}")
-            raise RuntimeError(f"文档提取失败: {str(e)}")
-
-
-# 为了兼容性创建别名
-Extractor = DocumentExtractor
-
-
-def main():
-    """命令行测试函数"""
-    import sys
-
-    if len(sys.argv) != 2:
-        print("使用方法: python extractor.py <文档文件路径>")
-        return 1
-
-    file_path = sys.argv[1]
-
-    try:
-        extractor = DocumentExtractor()
-        content = extractor.extract(file_path)
-        print(content)
-        return 0
-    except Exception as e:
-        print(f"错误: {str(e)}")
-        return 1
-
-
-if __name__ == "__main__":
-    sys.exit(main())

extractor_simple.py

@@ -1,241 +0,0 @@
-#!/usr/bin/env python3
-"""
-简化的文档提取器 - 专为Hugging Face Spaces优化
-支持PDF和DOCX文件转换为Markdown格式
-"""
-
-import logging
-import os
-import io
-from pathlib import Path
-from typing import Union, Optional
-
-# 配置日志
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-# 尝试导入依赖库
-try:
-    import PyPDF2
-
-    PDF_AVAILABLE = True
-except ImportError:
-    PDF_AVAILABLE = False
-    logger.warning("PyPDF2 not available - PDF processing disabled")
-
-try:
-    import docx
-
-    DOCX_AVAILABLE = True
-except ImportError:
-    DOCX_AVAILABLE = False
-    logger.warning("python-docx not available - DOCX processing disabled")
-
-
-class DocumentExtractor:
-    """简化的文档提取器类"""
-
-    def __init__(self):
-        """初始化提取器"""
-        self.supported_formats = []
-
-        if PDF_AVAILABLE:
-            self.supported_formats.append(".pdf")
-        if DOCX_AVAILABLE:
-            self.supported_formats.append(".docx")
-
-        if not self.supported_formats:
-            raise RuntimeError("没有可用的文档处理库。请安装PyPDF2和python-docx。")
-
-        logger.info(f"文档提取器初始化完成，支持格式: {self.supported_formats}")
-
-    def validate_document(self, file_path: Union[str, Path]) -> bool:
-        """
-        验证文档是否可以处理
-
-        Args:
-            file_path: 文件路径
-
-        Returns:
-            bool: 如果文档有效返回True
-        """
-        try:
-            path = Path(file_path)
-
-            # 检查文件是否存在
-            if not path.exists():
-                logger.error(f"文件不存在: {file_path}")
-                return False
-
-            # 检查文件扩展名
-            file_ext = path.suffix.lower()
-            if file_ext not in self.supported_formats:
-                logger.error(f"不支持的文件格式: {file_ext}")
-                return False
-
-            # 检查文件大小
-            file_size = path.stat().st_size
-            if file_size == 0:
-                logger.error("文件为空")
-                return False
-
-            if file_size > 100 * 1024 * 1024:  # 100MB限制
-                logger.warning(
-                    f"文件较大 ({file_size / 1024 / 1024:.2f} MB)，处理可能需要较长时间"
-                )
-
-            return True
-
-        except Exception as e:
-            logger.error(f"文件验证失败: {str(e)}")
-            return False
-
-    def extract_pdf_text(self, file_path: Union[str, Path]) -> str:
-        """
-        从PDF文件提取文本
-
-        Args:
-            file_path: PDF文件路径
-
-        Returns:
-            str: 提取的文本内容
-        """
-        if not PDF_AVAILABLE:
-            raise RuntimeError("PDF处理不可用 - 请安装PyPDF2")
-
-        try:
-            with open(file_path, "rb") as file:
-                pdf_reader = PyPDF2.PdfReader(file)
-                text_content = []
-
-                for page_num, page in enumerate(pdf_reader.pages):
-                    try:
-                        page_text = page.extract_text()
-                        if page_text.strip():
-                            text_content.append(
-                                f"## 第 {page_num + 1} 页\n\n{page_text}\n"
-                            )
-                    except Exception as e:
-                        logger.warning(f"无法提取第 {page_num + 1} 页内容: {str(e)}")
-                        continue
-
-                if not text_content:
-                    return "# PDF文档\n\n无法从此PDF文件中提取文本内容。"
-
-                return "# PDF文档\n\n" + "\n".join(text_content)
-
-        except Exception as e:
-            logger.error(f"PDF提取失败: {str(e)}")
-            return f"# PDF提取错误\n\n提取过程中出现错误: {str(e)}"
-
-    def extract_docx_text(self, file_path: Union[str, Path]) -> str:
-        """
-        从DOCX文件提取文本
-
-        Args:
-            file_path: DOCX文件路径
-
-        Returns:
-            str: 提取的文本内容
-        """
-        if not DOCX_AVAILABLE:
-            raise RuntimeError("DOCX处理不可用 - 请安装python-docx")
-
-        try:
-            doc = docx.Document(file_path)
-            text_content = []
-
-            for paragraph in doc.paragraphs:
-                if paragraph.text.strip():
-                    # 简单的格式检测
-                    text = paragraph.text.strip()
-
-                    # 检测标题（简单规则）
-                    if (
-                        len(text) < 100
-                        and not text.endswith(".")
-                        and not text.endswith("。")
-                    ):
-                        text_content.append(f"## {text}\n")
-                    else:
-                        text_content.append(f"{text}\n")
-
-            # 处理表格
-            for table in doc.tables:
-                text_content.append("\n### 表格\n")
-                for row in table.rows:
-                    row_text = " | ".join([cell.text.strip() for cell in row.cells])
-                    if row_text.strip():
-                        text_content.append(f"| {row_text} |")
-                text_content.append("\n")
-
-            if not text_content:
-                return "# Word文档\n\n无法从此DOCX文件中提取文本内容。"
-
-            return "# Word文档\n\n" + "\n".join(text_content)
-
-        except Exception as e:
-            logger.error(f"DOCX提取失败: {str(e)}")
-            return f"# DOCX提取错误\n\n提取过程中出现错误: {str(e)}"
-
-    def extract(self, file_path: Union[str, Path]) -> str:
-        """
-        提取文档内容并转换为Markdown格式
-
-        Args:
-            file_path: 文档文件路径
-
-        Returns:
-            str: Markdown格式的文档内容
-        """
-        logger.info(f"开始提取文档: {file_path}")
-
-        # 验证文档
-        if not self.validate_document(file_path):
-            raise ValueError(f"文档验证失败: {file_path}")
-
-        # 确定文件类型并提取
-        file_ext = Path(file_path).suffix.lower()
-
-        try:
-            if file_ext == ".pdf":
-                content = self.extract_pdf_text(file_path)
-            elif file_ext == ".docx":
-                content = self.extract_docx_text(file_path)
-            else:
-                raise ValueError(f"不支持的文件格式: {file_ext}")
-
-            logger.info(f"文档提取完成，内容长度: {len(content)} 字符")
-            return content
-
-        except Exception as e:
-            logger.error(f"文档提取失败: {str(e)}")
-            raise RuntimeError(f"文档提取失败: {str(e)}")
-
-
-# 为了兼容性创建别名
-Extractor = DocumentExtractor
-
-
-def main():
-    """命令行测试函数"""
-    import sys
-
-    if len(sys.argv) != 2:
-        print("使用方法: python extractor.py <文档文件路径>")
-        return 1
-
-    file_path = sys.argv[1]
-
-    try:
-        extractor = DocumentExtractor()
-        content = extractor.extract(file_path)
-        print(content)
-        return 0
-    except Exception as e:
-        print(f"错误: {str(e)}")
-        return 1
-
-
-if __name__ == "__main__":
-    sys.exit(main())

requirements.txt

@@ -1,13 +1,12 @@
+# Core dependencies
 gradio>=4.0.0
 PyPDF2>=3.0.0
 python-docx>=1.0.0
+
+# Optional enhanced PDF processing (fallback to PyPDF2 if not available)
+docling
+
+# Additional dependencies for document processing
 reportlab>=4.0.0
 Pillow>=9.0.0
 lxml>=4.9.0
-docling
-
-# Optional advanced PDF processing library (may fail on some systems)
-# If docling fails to install, the app will fallback to PyPDF2
-
-# MCP support (only needed for local environment, not for Hugging Face Spaces)
-# fastmcp>=0.1.0

run_server.py

@@ -1,91 +0,0 @@
-#!/usr/bin/env python3
-"""
-Server startup script for Document Extraction Tool
-Optimized for server deployment with better error handling
-"""
-
-import sys
-import os
-import logging
-
-# Configure logging for server environment
-logging.basicConfig(
-    level=logging.INFO,
-    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
-    handlers=[
-        logging.StreamHandler(sys.stdout),
-        logging.FileHandler("app.log")
-        if os.access(".", os.W_OK)
-        else logging.StreamHandler(sys.stdout),
-    ],
-)
-
-logger = logging.getLogger(__name__)
-
-
-def check_dependencies():
-    """Check if all required dependencies are available"""
-    missing_deps = []
-
-    try:
-        import gradio
-
-        logger.info(f"Gradio version: {gradio.__version__}")
-    except ImportError:
-        missing_deps.append("gradio")
-
-    try:
-        import PyPDF2
-
-        logger.info("PyPDF2 available")
-    except ImportError:
-        missing_deps.append("PyPDF2")
-
-    try:
-        import docx
-
-        logger.info("python-docx available")
-    except ImportError:
-        missing_deps.append("python-docx")
-
-    try:
-        from docling.document_converter import DocumentConverter
-
-        logger.info("Docling available - will use advanced PDF extraction")
-    except ImportError as e:
-        logger.warning(f"Docling not available - will use PyPDF2 fallback: {e}")
-
-    if missing_deps:
-        logger.error(f"Missing required dependencies: {missing_deps}")
-        logger.error(
-            "Please install missing dependencies with: pip install "
-            + " ".join(missing_deps)
-        )
-        return False
-
-    return True
-
-
-def main():
-    """Main startup function"""
-    logger.info("=" * 50)
-    logger.info("Starting Document Extraction Tool Server")
-    logger.info("=" * 50)
-
-    # Check dependencies
-    if not check_dependencies():
-        sys.exit(1)
-
-    # Import and run the main app
-    try:
-        from app import main as app_main
-
-        logger.info("Starting application...")
-        app_main()
-    except Exception as e:
-        logger.error(f"Failed to start application: {e}")
-        raise
-
-
-if __name__ == "__main__":
-    main()

test_launch.py

@@ -1,128 +0,0 @@
-#!/usr/bin/env python3
-"""
-Quick launch test for the Document Extraction Tool
-Tests if the application can start without errors
-"""
-
-import sys
-import os
-import time
-import threading
-import requests
-from pathlib import Path
-
-# Add current directory to path
-sys.path.insert(0, str(Path(__file__).parent))
-
-
-def test_launch():
-    """Test if the application launches successfully"""
-    print("🧪 Testing application launch...")
-
-    try:
-        # Import the app
-        from app import create_interface
-
-        print("✅ App import successful")
-
-        # Create interface
-        app = create_interface()
-        print("✅ Interface creation successful")
-
-        # Test launch with minimal config
-        def launch_test():
-            try:
-                app.launch(
-                    server_name="127.0.0.1",
-                    server_port=7861,  # Different port to avoid conflicts
-                    share=False,
-                    prevent_thread_lock=True,
-                    quiet=True,
-                )
-            except Exception as e:
-                print(f"❌ Launch failed: {e}")
-                return False
-            return True
-
-        # Run in separate thread
-        launch_thread = threading.Thread(target=launch_test)
-        launch_thread.daemon = True
-        launch_thread.start()
-
-        # Wait a bit for server to start
-        time.sleep(3)
-
-        # Test if server is responding
-        try:
-            response = requests.get("http://127.0.0.1:7861", timeout=5)
-            if response.status_code == 200:
-                print("✅ Server is responding successfully")
-                print("🎉 Launch test PASSED")
-                return True
-            else:
-                print(f"⚠️  Server returned status {response.status_code}")
-        except requests.RequestException as e:
-            print(f"⚠️  Server connection test failed: {e}")
-            print("   (This might be normal if using prevent_thread_lock)")
-
-        print("✅ Basic launch test completed without errors")
-        return True
-
-    except Exception as e:
-        print(f"❌ Launch test failed: {e}")
-        return False
-
-
-def test_imports():
-    """Test critical imports"""
-    print("📦 Testing imports...")
-
-    try:
-        import gradio
-
-        print(f"✅ Gradio {gradio.__version__}")
-
-        try:
-            from docling.document_converter import DocumentConverter
-
-            print("✅ Docling available")
-        except ImportError:
-            print("⚠️  Docling not available (fallback mode)")
-
-        import PyPDF2
-
-        print("✅ PyPDF2 available")
-
-        import docx
-
-        print("✅ python-docx available")
-
-        return True
-
-    except ImportError as e:
-        print(f"❌ Import failed: {e}")
-        return False
-
-
-def main():
-    """Run all tests"""
-    print("🔍 Document Extraction Tool - Launch Test")
-    print("=" * 50)
-
-    # Test imports first
-    if not test_imports():
-        return 1
-
-    print()
-
-    # Test launch
-    if not test_launch():
-        return 1
-
-    print("\n" + "=" * 50)
-    print("✅ All tests passed! Application should work correctly.")
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())

test_sample.pdf

@@ -1,68 +0,0 @@
-%PDF-1.3
-%���� ReportLab Generated PDF document http://www.reportlab.com
-1 0 obj
-<<
-/F1 2 0 R
->>
-endobj
-2 0 obj
-<<
-/BaseFont /Helvetica /Encoding /WinAnsiEncoding /Name /F1 /Subtype /Type1 /Type /Font
->>
-endobj
-3 0 obj
-<<
-/Contents 7 0 R /MediaBox [ 0 0 612 792 ] /Parent 6 0 R /Resources <<
-/Font 1 0 R /ProcSet [ /PDF /Text /ImageB /ImageC /ImageI ]
->> /Rotate 0 /Trans <<
-
->> 
-  /Type /Page
->>
-endobj
-4 0 obj
-<<
-/PageMode /UseNone /Pages 6 0 R /Type /Catalog
->>
-endobj
-5 0 obj
-<<
-/Author (anonymous) /CreationDate (D:20250604161223+02'00') /Creator (ReportLab PDF Library - www.reportlab.com) /Keywords () /ModDate (D:20250604161223+02'00') /Producer (ReportLab PDF Library - www.reportlab.com) 
-  /Subject (unspecified) /Title (untitled) /Trapped /False
->>
-endobj
-6 0 obj
-<<
-/Count 1 /Kids [ 3 0 R ] /Type /Pages
->>
-endobj
-7 0 obj
-<<
-/Filter [ /ASCII85Decode /FlateDecode ] /Length 350
->>
-stream
-GasbU;+ne\'SYH=/'amseu!4Ah4o.IJYHNnHjsr4W_5+1>M[Ua9ff2V'ko)'j?#BZ%7BD&(>cG#mQ#/7#*shD_=AiVJ&ILGr-pV@ASI$IOb,)gPc!l5e:cqTXJi*U)Vg]3\9)g!rXOC"$I9pA2m%^>!p'+9V6&#PM91$hFr0BXTf/?-Wu[^-&l,C]<r/m\@;RRV:T:V+=\O1-Ys)B"V9,1'$f>S^0//kbn/=TFHL4o"_l6!4CK0ca7WQpE:)*PhQ@.IW#.o>oAFLl27q98Tn"mtDBT)[nSSWjL$L4]4WDMXf@S+(^d/5l9&WT:492If:]_rqrD^.59Nb5/`?2*(^PAdcg[%m~>endstream
-endobj
-xref
-0 8
-0000000000 65535 f 
-0000000073 00000 n 
-0000000104 00000 n 
-0000000211 00000 n 
-0000000404 00000 n 
-0000000472 00000 n 
-0000000768 00000 n 
-0000000827 00000 n 
-trailer
-<<
-/ID 
-[<b95b80aec21480de24245e72127d8d0a><b95b80aec21480de24245e72127d8d0a>]
-% ReportLab generated PDF document -- digest (http://www.reportlab.com)
-
-/Info 5 0 R
-/Root 4 0 R
-/Size 8
->>
-startxref
-1267
-%%EOF

test_server.py

@@ -1,111 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test script to verify the document extraction functionality
-"""
-
-import sys
-import os
-import tempfile
-import logging
-
-# Add current directory to path to import app modules
-sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
-
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-
-def test_extractor():
-    """Test the document extractor functionality"""
-    try:
-        from app import get_extractor, extract_document
-
-        logger.info("Testing extractor initialization...")
-        extractor = get_extractor()
-        logger.info(f"Extractor initialized: {type(extractor)}")
-        logger.info(f"Using docling: {extractor.use_docling}")
-
-        # Test with sample files if they exist
-        test_files = ["test_sample.pdf", "test_sample.docx"]
-
-        for test_file in test_files:
-            if os.path.exists(test_file):
-                logger.info(f"Testing with {test_file}...")
-
-                # Mock file object for testing
-                class MockFile:
-                    def __init__(self, path):
-                        self.name = path
-
-                mock_file = MockFile(test_file)
-                content, status = extract_document(mock_file)
-
-                logger.info(f"Status: {status}")
-                logger.info(f"Content length: {len(content) if content else 0}")
-
-                if content:
-                    logger.info("✅ Extraction successful")
-                else:
-                    logger.warning("⚠️ No content extracted")
-            else:
-                logger.info(f"Test file {test_file} not found - skipping")
-
-        return True
-
-    except Exception as e:
-        logger.error(f"Test failed: {e}")
-        return False
-
-
-def test_interface():
-    """Test the Gradio interface creation"""
-    try:
-        from app import create_interface
-
-        logger.info("Testing interface creation...")
-        app = create_interface()
-        logger.info("✅ Interface created successfully")
-        return True
-
-    except Exception as e:
-        logger.error(f"Interface test failed: {e}")
-        return False
-
-
-def main():
-    """Run all tests"""
-    logger.info("=" * 50)
-    logger.info("Running Document Extractor Tests")
-    logger.info("=" * 50)
-
-    tests = [
-        ("Extractor functionality", test_extractor),
-        ("Interface creation", test_interface),
-    ]
-
-    passed = 0
-    total = len(tests)
-
-    for test_name, test_func in tests:
-        logger.info(f"\nRunning test: {test_name}")
-        if test_func():
-            passed += 1
-            logger.info(f"✅ {test_name} - PASSED")
-        else:
-            logger.error(f"❌ {test_name} - FAILED")
-
-    logger.info("\n" + "=" * 50)
-    logger.info(f"Test Results: {passed}/{total} tests passed")
-    logger.info("=" * 50)
-
-    if passed == total:
-        logger.info("🎉 All tests passed! Ready for server deployment.")
-        return True
-    else:
-        logger.error("❌ Some tests failed. Please check the issues above.")
-        return False
-
-
-if __name__ == "__main__":
-    success = main()
-    sys.exit(0 if success else 1)