File size: 8,556 Bytes
63bfc55 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 | """
SAAP Document Upload API
Handles file uploads, parsing, and privacy detection for multi-agent chat
"""
import logging
from typing import Optional
from fastapi import APIRouter, UploadFile, File, HTTPException, Form
from fastapi.responses import JSONResponse
from pydantic import BaseModel
from services.document_parser import document_parser
from services.privacy_detector import privacy_detector
logger = logging.getLogger(__name__)
router = APIRouter(prefix="/api/v1/documents", tags=["documents"])
class DocumentUploadResponse(BaseModel):
"""Response model for document upload"""
success: bool
document_id: str
filename: str
file_type: str
file_size: int
char_count: int
has_sensitive_data: bool
sensitive_data_types: list[str]
content_preview: str
full_content: str # 📄 Full document content for chat context
error: Optional[str] = None
@router.post("/upload", response_model=DocumentUploadResponse)
async def upload_document(
file: UploadFile = File(...),
user_message: Optional[str] = Form(None)
):
"""
Upload and parse a document (PDF, DOCX, TXT)
- Extracts text content from document
- Analyzes for sensitive/private data
- Returns parsed content and privacy analysis
Args:
file: Uploaded file (PDF, DOCX, TXT)
user_message: Optional user message with context about the document
Returns:
DocumentUploadResponse with parsed content and privacy analysis
"""
try:
logger.info(f"📤 Document upload started: {file.filename}")
# Read file content
file_content = await file.read()
# Parse document
parse_result = document_parser.parse_document(
file_data=file_content,
filename=file.filename,
mime_type=file.content_type
)
if not parse_result["success"]:
logger.error(f"❌ Document parsing failed: {parse_result['error']}")
raise HTTPException(
status_code=400,
detail=f"Failed to parse document: {parse_result['error']}"
)
extracted_text = parse_result["content"]
metadata = parse_result["metadata"]
# Analyze for sensitive data
from services.privacy_detector import analyze_document_privacy
privacy_level, privacy_details = analyze_document_privacy(
document_text=extracted_text,
filename=file.filename
)
# Convert privacy level to boolean + types for response
has_sensitive_data = privacy_level.value in ["private", "confidential"]
# Extract detected types from details
sensitive_types = []
if privacy_details.get("keyword_matches"):
sensitive_types.extend([cat for cat, _ in privacy_details["keyword_matches"]])
if privacy_details.get("pattern_matches"):
sensitive_types.extend([cat for _, cat in privacy_details["pattern_matches"]])
if privacy_details.get("document_indicators"):
sensitive_types.extend(privacy_details["document_indicators"])
# Remove duplicates
sensitive_types = list(set(sensitive_types))
# Create content preview (first 500 characters)
content_preview = extracted_text[:500]
if len(extracted_text) > 500:
content_preview += "..."
# Generate document ID (simple hash for now)
import hashlib
doc_id = hashlib.sha256(file_content).hexdigest()[:16]
logger.info(
f"✅ Document processed successfully: {file.filename} "
f"({metadata['char_count']} chars, "
f"sensitive: {has_sensitive_data})"
)
return DocumentUploadResponse(
success=True,
document_id=doc_id,
filename=metadata["filename"],
file_type=metadata["file_type"],
file_size=metadata["file_size"],
char_count=metadata["char_count"],
has_sensitive_data=has_sensitive_data,
sensitive_data_types=sensitive_types,
content_preview=content_preview,
full_content=extracted_text, # 📄 Full document content for chat context
error=None
)
except HTTPException:
raise
except Exception as e:
logger.error(f"❌ Document upload error: {e}", exc_info=True)
raise HTTPException(
status_code=500,
detail=f"Internal server error: {str(e)}"
)
@router.post("/analyze")
async def analyze_document_content(
file: UploadFile = File(...),
):
"""
Analyze document for sensitive data without full parsing
Quick privacy check before full processing
Args:
file: Uploaded file
Returns:
Privacy analysis results
"""
try:
logger.info(f"🔍 Document privacy analysis: {file.filename}")
# Read file content
file_content = await file.read()
# Parse document
parse_result = document_parser.parse_document(
file_data=file_content,
filename=file.filename,
mime_type=file.content_type
)
if not parse_result["success"]:
raise HTTPException(
status_code=400,
detail=f"Failed to parse document: {parse_result['error']}"
)
# Analyze for sensitive data
from services.privacy_detector import analyze_document_privacy
privacy_level, privacy_details = analyze_document_privacy(
document_text=parse_result["content"],
filename=file.filename
)
# Convert privacy level to boolean
has_sensitive_data = privacy_level.value in ["private", "confidential"]
# Extract detected types
sensitive_types = []
if privacy_details.get("keyword_matches"):
sensitive_types.extend([cat for cat, _ in privacy_details["keyword_matches"]])
if privacy_details.get("pattern_matches"):
sensitive_types.extend([cat for _, cat in privacy_details["pattern_matches"]])
if privacy_details.get("document_indicators"):
sensitive_types.extend(privacy_details["document_indicators"])
sensitive_types = list(set(sensitive_types))
logger.info(
f"✅ Privacy analysis complete: {file.filename} "
f"(sensitive: {has_sensitive_data})"
)
return JSONResponse(content={
"success": True,
"filename": file.filename,
"privacy_level": privacy_level.value,
"has_sensitive_data": has_sensitive_data,
"sensitive_data_types": sensitive_types,
"reason": privacy_details.get("reason", "unknown"),
"details": privacy_details
})
except HTTPException:
raise
except Exception as e:
logger.error(f"❌ Document analysis error: {e}", exc_info=True)
raise HTTPException(
status_code=500,
detail=f"Internal server error: {str(e)}"
)
@router.get("/supported-formats")
async def get_supported_formats():
"""
Get list of supported document formats
Returns:
List of supported file formats and their MIME types
"""
return JSONResponse(content={
"success": True,
"supported_formats": [
{
"extension": "pdf",
"mime_type": "application/pdf",
"description": "Adobe PDF Document",
"max_size_mb": 10
},
{
"extension": "docx",
"mime_type": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
"description": "Microsoft Word Document (2007+)",
"max_size_mb": 10
},
{
"extension": "doc",
"mime_type": "application/msword",
"description": "Microsoft Word Document (Legacy)",
"max_size_mb": 10
},
{
"extension": "txt",
"mime_type": "text/plain",
"description": "Plain Text Document",
"max_size_mb": 10
}
],
"max_file_size_bytes": document_parser.MAX_FILE_SIZE
})
|