Converting your document...
+جاري التحويل... يرجى الانتظار
+ملاحظة: هذا الواجهة تتصل مباشرة بمساحتك على Hugging Face Space.
+API is running. Visit /docs for API documentation.
+ + + """ \ No newline at end of file diff --git a/src/utils/config.py b/src/utils/config.py new file mode 100644 index 0000000000000000000000000000000000000000..6988bf7991e8e8c50386742b922300ba1ffb812a --- /dev/null +++ b/src/utils/config.py @@ -0,0 +1,36 @@ +#!/usr/bin/env python3 +""" +Configuration module for the DOCX to PDF converter +""" + +import os +from typing import List + +class Config: + """Application configuration""" + + # File handling + MAX_FILE_SIZE = int(os.environ.get("MAX_FILE_SIZE", 50 * 1024 * 1024)) # 50MB default + SUPPORTED_MIME_TYPES: List[str] = [ + "application/vnd.openxmlformats-officedocument.wordprocessingml.document" + ] + ALLOWED_EXTENSIONS: List[str] = [".docx"] + + # Conversion settings + MAX_CONVERSION_TIME = int(os.environ.get("MAX_CONVERSION_TIME", 120)) # 2 minutes + # Use /tmp/conversions as it's more likely to be writable in containerized environments + TEMP_DIR = os.environ.get("TEMP_DIR", "/tmp/conversions") + + # Static files directory for storing converted PDFs + STATIC_DIR = os.environ.get("STATIC_DIR", "/app/static") + + # API settings + API_TITLE = "Enhanced DOCX to PDF Converter" + API_DESCRIPTION = "Professional API for converting DOCX files to PDF with perfect formatting preservation" + API_VERSION = "2.0.0" + + # CORS settings + CORS_ORIGINS = os.environ.get("CORS_ORIGINS", "*").split(",") + CORS_CREDENTIALS = os.environ.get("CORS_CREDENTIALS", "true").lower() == "true" + CORS_METHODS = os.environ.get("CORS_METHODS", "*").split(",") + CORS_HEADERS = os.environ.get("CORS_HEADERS", "*").split(",") \ No newline at end of file diff --git a/src/utils/converter.py b/src/utils/converter.py new file mode 100644 index 0000000000000000000000000000000000000000..04ee20f95578e486e8e1872d9eb44d5f9adca95d --- /dev/null +++ b/src/utils/converter.py @@ -0,0 +1,116 @@ +#!/usr/bin/env python3 +""" +Document conversion utilities for the DOCX to PDF converter +""" + +import os +import subprocess +import logging +import base64 +from typing import Optional + +logger = logging.getLogger(__name__) + +class DocumentConverter: + """Handle document conversion operations""" + + def __init__(self): + self.max_conversion_time = 120 # 2 minutes + + def convert_docx_to_pdf(self, input_path: str, output_path: str) -> bool: + """Convert DOCX to PDF using LibreOffice""" + try: + # Validate input file exists + if not os.path.exists(input_path): + logger.error(f"Input file does not exist: {input_path}") + return False + + # Get output directory + output_dir = os.path.dirname(output_path) + + # Ensure output directory exists + os.makedirs(output_dir, exist_ok=True) + + # Set environment variables for LibreOffice to avoid user installation issues + env = os.environ.copy() + env['HOME'] = '/tmp' + env['USERPROFILE'] = '/tmp' + + # Use LibreOffice headless mode for conversion + cmd = [ + "libreoffice", + "--headless", + "--norestore", + "--nofirststartwizard", + "--nologo", + "--nolockcheck", + "--convert-to", "pdf", + "--outdir", output_dir, + input_path + ] + + logger.info(f"Converting {input_path} to PDF...") + + result = subprocess.run( + cmd, + capture_output=True, + text=True, + timeout=self.max_conversion_time, + env=env + ) + + if result.returncode != 0: + logger.error(f"Conversion failed with return code {result.returncode}: {result.stderr}") + return False + + # Check if PDF was created + if not os.path.exists(output_path): + logger.error("PDF file was not created") + # List files in output directory for debugging + if os.path.exists(output_dir): + files = os.listdir(output_dir) + logger.info(f"Files in output directory: {files}") + return False + + logger.info(f"Successfully converted {input_path} to {output_path}") + return True + + except subprocess.TimeoutExpired: + logger.error("Conversion timed out") + return False + except Exception as e: + logger.error(f"Conversion error: {e}") + return False + + def decode_base64_content(self, base64_content: str) -> Optional[bytes]: + """Decode base64 encoded content""" + try: + return base64.b64decode(base64_content) + except Exception as e: + logger.error(f"Failed to decode base64 content: {e}") + return None + + def validate_libreoffice(self) -> bool: + """Validate LibreOffice installation""" + try: + # Set environment variables for LibreOffice + env = os.environ.copy() + env['HOME'] = '/tmp' + env['USERPROFILE'] = '/tmp' + + result = subprocess.run( + ["libreoffice", "--version"], + capture_output=True, + text=True, + timeout=10, + env=env + ) + if result.returncode != 0: + logger.error("LibreOffice not found or not working") + return False + + logger.info(f"LibreOffice version: {result.stdout.strip()}") + return True + except Exception as e: + logger.error(f"LibreOffice validation error: {e}") + return False \ No newline at end of file diff --git a/src/utils/file_handler.py b/src/utils/file_handler.py new file mode 100644 index 0000000000000000000000000000000000000000..33b977cb52516465b1f11c3abf7e9161e5422142 --- /dev/null +++ b/src/utils/file_handler.py @@ -0,0 +1,87 @@ +#!/usr/bin/env python3 +""" +File handling utilities for the DOCX to PDF converter +""" + +import os +import tempfile +import shutil +import logging +from pathlib import Path +from typing import Optional + +logger = logging.getLogger(__name__) + +class FileHandler: + """Handle file operations for the converter""" + + def __init__(self, base_temp_dir: str = "/tmp/conversions"): + # Use /tmp as fallback since it's more likely to be writable in containerized environments + self.base_temp_dir = base_temp_dir + try: + os.makedirs(self.base_temp_dir, exist_ok=True) + # Ensure the directory is writable + os.chmod(self.base_temp_dir, 0o777) + except Exception as e: + logger.error(f"Failed to create base temp directory {self.base_temp_dir}: {e}") + # Fallback to system temp directory + self.base_temp_dir = tempfile.gettempdir() + logger.info(f"Falling back to system temp directory: {self.base_temp_dir}") + + def create_temp_directory(self) -> str: + """Create a temporary directory for file processing""" + try: + temp_dir = tempfile.mkdtemp(dir=self.base_temp_dir) + logger.info(f"Created temporary directory: {temp_dir}") + # Ensure the directory is writable + os.chmod(temp_dir, 0o777) + return temp_dir + except Exception as e: + logger.error(f"Failed to create temporary directory: {e}") + # Try fallback to system temp directory + try: + temp_dir = tempfile.mkdtemp() + os.chmod(temp_dir, 0o777) + logger.info(f"Created temporary directory in fallback location: {temp_dir}") + return temp_dir + except Exception as fallback_e: + logger.error(f"Fallback also failed: {fallback_e}") + raise + + def save_uploaded_file(self, temp_dir: str, filename: str, content: bytes) -> str: + """Save uploaded file to temporary directory""" + try: + file_path = os.path.join(temp_dir, filename) + with open(file_path, "wb") as f: + f.write(content) + logger.info(f"Saved file: {file_path}") + return file_path + except Exception as e: + logger.error(f"Failed to save file {filename}: {e}") + raise + + def cleanup_temp_directory(self, temp_dir: str): + """Clean up temporary directory""" + try: + if os.path.exists(temp_dir): + shutil.rmtree(temp_dir) + logger.info(f"Cleaned up temporary directory: {temp_dir}") + except Exception as e: + logger.error(f"Failed to cleanup directory {temp_dir}: {e}") + + def get_file_size(self, file_path: str) -> int: + """Get file size in bytes""" + try: + return os.path.getsize(file_path) + except Exception as e: + logger.error(f"Failed to get file size for {file_path}: {e}") + return 0 + + def validate_file_extension(self, filename: str, allowed_extensions: list) -> bool: + """Validate file extension""" + try: + ext = Path(filename).suffix.lower() + return ext in allowed_extensions + except Exception as e: + logger.error(f"Failed to validate file extension for {filename}: {e}") + return False \ No newline at end of file diff --git a/start.bat b/start.bat new file mode 100644 index 0000000000000000000000000000000000000000..68d362e4df994a46dab40d94c8c35ad882a0f8b3 --- /dev/null +++ b/start.bat @@ -0,0 +1,26 @@ +@echo off +echo Enhanced DOCX to PDF Converter +echo ============================== + +REM Check if Docker is available +docker --version >nul 2>&1 +if %errorlevel% neq 0 ( + echo Docker is not installed. Please install Docker to run this application. + pause + exit /b 1 +) + +REM Check if Docker Compose is available +docker-compose --version >nul 2>&1 +if %errorlevel% neq 0 ( + echo Docker Compose is not installed. Please install Docker Compose to run this application. + pause + exit /b 1 +) + +echo Building and starting the application... +docker-compose up --build + +echo Application is now running at http://localhost:8000 +echo API documentation is available at http://localhost:8000/docs +pause \ No newline at end of file diff --git a/start.sh b/start.sh new file mode 100644 index 0000000000000000000000000000000000000000..712823328bd2b93a9de80216b762aa437b98fc8c --- /dev/null +++ b/start.sh @@ -0,0 +1,26 @@ +#!/bin/bash + +# Startup script for Enhanced DOCX to PDF Converter + +echo "Enhanced DOCX to PDF Converter" +echo "==============================" + +# Check if Docker is available +if ! command -v docker &> /dev/null +then + echo "Docker is not installed. Please install Docker to run this application." + exit 1 +fi + +# Check if Docker Compose is available +if ! command -v docker-compose &> /dev/null +then + echo "Docker Compose is not installed. Please install Docker Compose to run this application." + exit 1 +fi + +echo "Building and starting the application..." +docker-compose up --build + +echo "Application is now running at http://localhost:8000" +echo "API documentation is available at http://localhost:8000/docs" \ No newline at end of file diff --git a/static/.gitkeep b/static/.gitkeep new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/templates/index.html b/templates/index.html new file mode 100644 index 0000000000000000000000000000000000000000..9a0c455127f71af37b1b97528cb718ca4d75569a --- /dev/null +++ b/templates/index.html @@ -0,0 +1,468 @@ + + + + + +Convert between DOCX and PDF formats with perfect formatting preservation
+Converting your document... This may take a moment.
+Converting your document... This may take a moment.
+Your files are processed securely and deleted after conversion.
+High-performance conversion with optimized processing.
+No software installation required. Works directly in your browser.
+Convert both ways between DOCX and PDF formats.
+تحويل مستندات Word إلى PDF بسهولة
+اختر ملف DOCX لتحويله إلى PDF
+ +اسحب الملف هنا أو انقر للاختيار
+يدعم فقط ملفات DOCX
+ +يمكنك الآن فتح ملف PDF المحول
+ +