Initial commit

2025-07-11 13:52:19 +00:00
commit e0c489f625
362 changed files with 27286 additions and 0 deletions
@@ -0,0 +1,139 @@
+from fastapi import APIRouter, UploadFile, File, HTTPException
+from typing import List, Optional, Dict
+from pathlib import Path
+import shutil
+import tempfile
+from pydantic import BaseModel
+from modules.document_processor import DocumentProcessor
+import os
+
+class BatchConvertRequest(BaseModel):
+    directory: str
+    output_dir: Optional[str] = None
+
+router = APIRouter()
+doc_processor = DocumentProcessor()
+
+@router.post("/convert-to-pdf")
+async def convert_to_pdf(
+    files: List[UploadFile] = File(...),
+    output_format: str = "pdf"
+):
+    """
+    Convert uploaded documents to PDF format
+    """
+    results = []
+    with tempfile.TemporaryDirectory() as temp_dir:
+        for file in files:
+            # Save uploaded file to temp directory
+            temp_file = Path(temp_dir) / file.filename
+            with temp_file.open("wb") as buffer:
+                shutil.copyfileobj(file.file, buffer)
+            
+            try:
+                # Process the document
+                pdf_content = doc_processor.convert_to_pdf(temp_file)
+                results.append({
+                    "filename": file.filename,
+                    "converted_content": pdf_content,
+                    "status": "success"
+                })
+            except Exception as e:
+                results.append({
+                    "filename": file.filename,
+                    "error": str(e),
+                    "status": "error"
+                })
+    
+    return results
+
+@router.post("/batch-convert")
+async def batch_convert(
+    directory: str,
+    output_format: str = "pdf"
+):
+    """
+    Convert all documents in a directory to PDF format
+    """
+    try:
+        results = doc_processor.batch_convert_directory(directory)
+        return results
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@router.post("/batch-convert-recursive")
+async def batch_convert_recursive(request_data: BatchConvertRequest):
+    """
+    Convert all documents in a directory and its subdirectories to PDF
+    """
+    try:
+        directory_path = Path(request_data.directory)
+        if not directory_path.exists():
+            raise HTTPException(status_code=404, detail=f"Directory not found: {request_data.directory}")
+        
+        output_path = None
+        if request_data.output_dir:
+            output_path = Path(request_data.output_dir)
+            output_path.mkdir(parents=True, exist_ok=True)
+        
+        results = []
+        supported_extensions = doc_processor.supported_extensions.keys()
+        
+        # Debug: Print processing info
+        print(f"Processing directory: {directory_path}")
+        print(f"Output directory: {output_path}")
+        print(f"Supported extensions: {list(supported_extensions)}")
+        
+        # Count files before processing
+        all_files = []
+        for ext in supported_extensions:
+            all_files.extend(list(directory_path.rglob(f"*.{ext}")))
+        print(f"Found {len(all_files)} files to process")
+        
+        # Recursively find all documents
+        for file_path in all_files:
+            try:
+                print(f"Processing: {file_path}")
+                # Convert the document
+                pdf_content = doc_processor.convert_to_pdf(file_path)
+                
+                # Determine output path
+                if output_path:
+                    # Preserve directory structure in output_dir
+                    rel_path = file_path.relative_to(directory_path)
+                    out_path = output_path / rel_path.with_suffix('.pdf')
+                    out_path.parent.mkdir(parents=True, exist_ok=True)
+                else:
+                    out_path = file_path.with_suffix('.pdf')
+                
+                # Save the PDF
+                with open(out_path, 'wb') as f:
+                    f.write(pdf_content)
+                
+                results.append({
+                    "source_file": str(file_path),
+                    "output_file": str(out_path),
+                    "status": "success"
+                })
+                print(f"Successfully converted: {file_path} -> {out_path}")
+                
+            except Exception as e:
+                print(f"Error converting {file_path}: {str(e)}")
+                results.append({
+                    "source_file": str(file_path),
+                    "status": "error",
+                    "error": str(e)
+                })
+        
+        response_data = {
+            "total_files": len(results),
+            "successful": sum(1 for r in results if r["status"] == "success"),
+            "failed": sum(1 for r in results if r["status"] == "error"),
+            "results": results
+        }
+        print(f"Conversion complete: {response_data['successful']} successful, {response_data['failed']} failed")
+        return response_data
+        
+    except Exception as e:
+        print(f"Error in batch conversion: {str(e)}")
+        raise HTTPException(status_code=500, detail=str(e))