调整目录结构

.gitignore

@@ -67,4 +67,7 @@ temp/
 src_folder
 target_folder
 app.log
-__pycache__
+__pycache__
+data/doc_dest
+data/doc_src
+data/doc_intermediate

src/config/settings.py

@@ -5,8 +5,8 @@ from typing import Optional
 
 class Settings(BaseSettings):
     # Storage paths
-    OBJECT_STORAGE_PATH: str = "/Users/tigeren/Dev/digisky/legal-doc-masker/src_folder"
-    TARGET_DIRECTORY_PATH: str = "/Users/tigeren/Dev/digisky/legal-doc-masker/target_folder"
+    OBJECT_STORAGE_PATH: str = ""
+    TARGET_DIRECTORY_PATH: str = ""
 
     # Ollama API settings
     OLLAMA_API_URL: str = "https://api.ollama.com"

src/document_handlers/document_factory.py

@@ -1,7 +1,7 @@
 import os
 from typing import Optional
-from models.document_processor import DocumentProcessor
-from models.processors import (
+from document_handlers.document_processor import DocumentProcessor
+from document_handlers.processors import (
     TxtDocumentProcessor,
     DocxDocumentProcessor,
     PdfDocumentProcessor

src/document_handlers/processors/__init__.py

@@ -0,0 +1,5 @@
+from document_handlers.processors.txt_processor import TxtDocumentProcessor
+from document_handlers.processors.docx_processor import DocxDocumentProcessor
+from document_handlers.processors.pdf_processor import PdfDocumentProcessor
+
+__all__ = ['TxtDocumentProcessor', 'DocxDocumentProcessor', 'PdfDocumentProcessor']

src/document_handlers/processors/docx_processor.py

@@ -1,5 +1,5 @@
 import docx
-from models.document_processor import DocumentProcessor
+from document_handlers.document_processor import DocumentProcessor
 
 class DocxDocumentProcessor(DocumentProcessor):
     def __init__(self, input_path: str, output_path: str):

src/document_handlers/processors/pdf_processor.py

@@ -1,6 +1,6 @@
 import os
 import PyPDF2
-from models.document_processor import DocumentProcessor
+from document_handlers.document_processor import DocumentProcessor
 from magic_pdf.data.data_reader_writer import FileBasedDataWriter, FileBasedDataReader
 from magic_pdf.data.dataset import PymuDocDataset
 from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze

src/document_handlers/processors/txt_processor.py

@@ -1,4 +1,4 @@
-from models.document_processor import DocumentProcessor
+from document_handlers.document_processor import DocumentProcessor
 from services.ollama_client import OllamaClient
 import textwrap
 import logging

src/main.py

@@ -7,6 +7,11 @@ def main():
     from services.file_monitor import FileMonitor
     from config.settings import settings
 
+    import logging
+    logger = logging.getLogger(__name__)
+    logger.info("Starting the application")
+    logger.info(f"Monitoring directory: {settings.OBJECT_STORAGE_PATH}")
+    logger.info(f"Target directory: {settings.TARGET_DIRECTORY_PATH}")
     # Initialize the file monitor
     file_monitor = FileMonitor(settings.OBJECT_STORAGE_PATH, settings.TARGET_DIRECTORY_PATH)
 

src/models/processors/__init__.py

@@ -1,5 +0,0 @@
-from models.processors.txt_processor import TxtDocumentProcessor
-from models.processors.docx_processor import DocxDocumentProcessor
-from models.processors.pdf_processor import PdfDocumentProcessor
-
-__all__ = ['TxtDocumentProcessor', 'DocxDocumentProcessor', 'PdfDocumentProcessor']

src/services/document_service.py

@@ -1,5 +1,5 @@
 import logging
-from models.document_factory import DocumentProcessorFactory
+from document_handlers.document_factory import DocumentProcessorFactory
 from services.ollama_client import OllamaClient
 
 logger = logging.getLogger(__name__)

src_folder/README.md

@@ -1,58 +0,0 @@
-# README.md
-
-# Document Processing App
-
-This project is designed to process legal documents by hiding sensitive information such as names and company names. It utilizes the Ollama API with selected models for text processing. The application monitors a specified directory for new files, processes them automatically, and saves the results to a target path.
-
-## Project Structure
-
-```
-doc-processing-app
-├── src
-│   ├── main.py               # Entry point of the application
-│   ├── config
-│   │   └── settings.py       # Configuration settings for paths
-│   ├── services
-│   │   ├── file_monitor.py    # Monitors directory for new files
-│   │   ├── document_processor.py # Handles document processing logic
-│   │   └── ollama_client.py   # Interacts with the Ollama API
-│   ├── utils
-│   │   └── file_utils.py      # Utility functions for file operations
-│   └── models
-│       └── document.py        # Represents the structure of a document
-├── tests
-│   └── test_document_processor.py # Unit tests for DocumentProcessor
-├── requirements.txt           # Project dependencies
-├── .env.example               # Example environment variables
-└── README.md                  # Project documentation
-```
-
-## Setup Instructions
-
-1. Clone the repository:
-   ```
-   git clone <repository-url>
-   cd doc-processing-app
-   ```
-
-2. Install the required dependencies:
-   ```
-   pip install -r requirements.txt
-   ```
-
-3. Configure the application by editing the `src/config/settings.py` file to set the paths for the object storage and target directory.
-
-4. Create a `.env` file based on the `.env.example` file to set up necessary environment variables.
-
-## Usage
-
-To run the application, execute the following command:
-```
-python src/main.py
-```
-
-The application will start monitoring the specified directory for new documents. Once a new document is added, it will be processed automatically.
-
-## Contributing
-
-Contributions are welcome! Please open an issue or submit a pull request for any improvements or bug fixes.