实现docx转md

src/document_handlers/processors/docx_processor.py

@@ -1,20 +1,76 @@
+import os
 import docx
 from document_handlers.document_processor import DocumentProcessor
+from magic_pdf.data.data_reader_writer import FileBasedDataWriter
+from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze
+from magic_pdf.data.read_api import read_local_office
+import logging
+from services.ollama_client import OllamaClient
+from config.settings import settings
+from prompts.masking_prompts import get_masking_mapping_prompt
+
+logger = logging.getLogger(__name__)
 
 class DocxDocumentProcessor(DocumentProcessor):
     def __init__(self, input_path: str, output_path: str):
         self.input_path = input_path
         self.output_path = output_path
+        self.output_dir = os.path.dirname(output_path)
+        self.name_without_suff = os.path.splitext(os.path.basename(input_path))[0]
+        
+        # Setup output directories
+        self.local_image_dir = os.path.join(self.output_dir, "images")
+        self.image_dir = os.path.basename(self.local_image_dir)
+        os.makedirs(self.local_image_dir, exist_ok=True)
+        
+        self.ollama_client = OllamaClient(model_name=settings.OLLAMA_MODEL, base_url=settings.OLLAMA_API_URL)
 
     def read_content(self) -> str:
-        doc = docx.Document(self.input_path)
+        try:
-        return '\n'.join([paragraph.text for paragraph in doc.paragraphs])
+            # Initialize writers
+            image_writer = FileBasedDataWriter(self.local_image_dir)
+            md_writer = FileBasedDataWriter(self.output_dir)
+            
+            # Create Dataset Instance and process
+            ds = read_local_office(self.input_path)[0]
+            pipe_result = ds.apply(doc_analyze, ocr=True).pipe_txt_mode(image_writer)
+            
+            # Generate markdown
+            md_content = pipe_result.get_markdown(self.image_dir)
+            pipe_result.dump_md(md_writer, f"{self.name_without_suff}.md", self.image_dir)
+            
+            return md_content
+        except Exception as e:
+            logger.error(f"Error converting DOCX to MD: {e}")
+            raise
 
     def process_content(self, content: str) -> str:
-        # Implementation for processing docx content
+        logger.info("Processing DOCX content")
-        return content
+        
+        # Split content into sentences and apply masking
+        sentences = content.split("。")
+        final_md = ""
+        for sentence in sentences:
+            if sentence.strip():  # Only process non-empty sentences
+                formatted_prompt = get_masking_mapping_prompt(sentence)
+                logger.info("Calling ollama to generate response, prompt: %s", formatted_prompt)
+                response = self.ollama_client.generate(formatted_prompt)
+                logger.info(f"Response generated: {response}")
+                final_md += response + "。"
+        
+        return final_md
 
     def save_content(self, content: str) -> None:
-        doc = docx.Document()
+        # Ensure output path has .md extension
-        doc.add_paragraph(content)
+        output_dir = os.path.dirname(self.output_path)
-        doc.save(self.output_path)
+        base_name = os.path.splitext(os.path.basename(self.output_path))[0]
+        md_output_path = os.path.join(output_dir, f"{base_name}.md")
+        
+        logger.info(f"Saving masked content to: {md_output_path}")
+        try:
+            with open(md_output_path, 'w', encoding='utf-8') as file:
+                file.write(content)
+            logger.info(f"Successfully saved content to {md_output_path}")
+        except Exception as e:
+            logger.error(f"Error saving content: {e}")
+            raise