Spaces:
Sleeping
Sleeping
File size: 9,243 Bytes
3a7eb07 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 | """
Document API Endpoints
Document upload, management, and analysis
"""
import logging
import uuid
from datetime import datetime
from typing import List, Optional
from fastapi import APIRouter, BackgroundTasks, Depends, HTTPException, Query, status
from sqlalchemy import func
from sqlalchemy.orm import Session
from app.api.deps import audit_middleware, get_current_user, get_current_user_id
from app.core.exceptions import NotFoundError
from app.db.session import get_db
from app.models.audit import AuditAction, create_audit_log
from app.models.document import (
ComplianceStatus,
Document,
DocumentCategory,
DocumentStatus,
)
from app.models.user import User
from app.schemas.document import (
DocumentAnalysisResponse,
DocumentCreate,
DocumentListResponse,
DocumentResponse,
DocumentUploadResponse,
)
logger = logging.getLogger(__name__)
router = APIRouter()
@router.get("", response_model=DocumentListResponse)
async def list_documents(
page: int = Query(1, ge=1),
page_size: int = Query(20, ge=1, le=100),
category: Optional[DocumentCategory] = None,
status: Optional[DocumentStatus] = None,
search: Optional[str] = None,
user_id: str = Depends(get_current_user_id),
db: Session = Depends(get_db),
):
"""
List user's documents with filtering and pagination.
"""
query = db.query(Document).filter(Document.user_id == user_id)
# Apply filters
if category:
query = query.filter(Document.category == category)
if status:
query = query.filter(Document.status == status)
if search:
# Escape SQL wildcard characters to prevent injection
escaped_search = (
search.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")
)
safe_pattern = f"%{escaped_search}%"
query = query.filter(
Document.title.ilike(safe_pattern, escape="\\")
| Document.file_name.ilike(safe_pattern, escape="\\")
)
# Get total count
total = query.count()
# Apply pagination
offset = (page - 1) * page_size
documents = (
query.order_by(Document.created_at.desc()).offset(offset).limit(page_size).all()
)
# Calculate stats
stats = _calculate_document_stats(db, user_id)
return DocumentListResponse(
documents=[DocumentResponse(**doc.to_dict()) for doc in documents],
total=total,
page=page,
page_size=page_size,
stats=stats,
)
@router.post(
"", response_model=DocumentUploadResponse, status_code=status.HTTP_202_ACCEPTED
)
async def create_document(
request: DocumentCreate,
user_id: str = Depends(get_current_user_id),
db: Session = Depends(get_db),
):
"""
Create a new document from UploadThing URL.
Triggers background processing with AI analysis via task queue.
"""
# Create document record
document = Document(
user_id=user_id,
title=request.title or request.file_name.rsplit(".", 1)[0],
file_name=request.file_name,
file_size=request.file_size,
file_type=request.file_type,
file_url=request.file_url,
status=DocumentStatus.PENDING,
tags=request.tags or [],
)
db.add(document)
db.flush() # Flush to get the document.id without committing
# Create audit log
audit = create_audit_log(
action=AuditAction.DOCUMENT_UPLOAD.value,
user_id=user_id,
resource_type="document",
resource_id=str(document.id),
details={
"file_name": document.file_name,
"file_size": document.file_size,
"file_type": document.file_type,
},
)
db.add(audit)
# Commit both document and audit atomically
db.commit()
db.refresh(document)
# Trigger background processing
from app.services.queue import enqueue_document_task
enqueue_document_task(str(document.id))
logger.info(f"Document created and enqueued: {document.id} - {document.title}")
return DocumentUploadResponse(
id=str(document.id),
title=document.title,
file_name=document.file_name,
status=DocumentStatus.PENDING,
job_id=str(document.id), # Using doc ID as job ID for now
message="Document uploaded successfully. AI analysis queued.",
)
@router.get("/{document_id}", response_model=DocumentResponse)
async def get_document(
document_id: uuid.UUID,
user_id: str = Depends(get_current_user_id),
db: Session = Depends(get_db),
):
"""
Get document details by ID.
"""
document = (
db.query(Document)
.filter(Document.id == document_id, Document.user_id == user_id)
.first()
)
if not document:
raise NotFoundError("Document", document_id)
return DocumentResponse(**document.to_dict())
@router.delete("/{document_id}")
async def delete_document(
document_id: uuid.UUID,
user_id: str = Depends(get_current_user_id),
db: Session = Depends(get_db),
):
"""
Delete a document and all associated data.
"""
document = (
db.query(Document)
.filter(Document.id == document_id, Document.user_id == user_id)
.first()
)
if not document:
raise NotFoundError("Document", document_id)
# Create audit log before deletion
audit = create_audit_log(
action=AuditAction.DOCUMENT_DELETE.value,
user_id=user_id,
resource_type="document",
resource_id=str(document_id),
details={"file_name": document.file_name},
)
db.add(audit)
# Delete document (cascade will handle embeddings)
db.delete(document)
db.commit()
logger.info(f"Document deleted: {document_id}")
return {"success": True, "message": "Document deleted successfully"}
@router.get("/{document_id}/analysis", response_model=DocumentAnalysisResponse)
async def get_document_analysis(
document_id: uuid.UUID,
user_id: str = Depends(get_current_user_id),
db: Session = Depends(get_db),
):
"""
Get AI analysis results for a document.
"""
document = (
db.query(Document)
.filter(Document.id == document_id, Document.user_id == user_id)
.first()
)
if not document:
raise NotFoundError("Document", document_id)
if document.status != DocumentStatus.COMPLETED:
return DocumentAnalysisResponse(
document_id=str(document.id), status=document.status.value, analysis=None
)
analysis = {
"category": document.category,
"subcategory": document.subcategory,
"classification_confidence": document.classification_confidence,
"summary": document.summary,
"key_points": document.key_points or [],
"safety_score": document.safety_score,
"compliance_status": document.compliance_status,
"hazards_detected": document.hazards_detected or [],
"safety_recommendations": document.safety_recommendations or [],
"entities": {
k: v if isinstance(v, list) else []
for k, v in (document.entities or {}).items()
},
}
return DocumentAnalysisResponse(
document_id=str(document.id), status="completed", analysis=analysis
)
@router.post("/{document_id}/reanalyze", status_code=status.HTTP_202_ACCEPTED)
async def reanalyze_document(
document_id: uuid.UUID,
user_id: str = Depends(get_current_user_id),
db: Session = Depends(get_db),
):
"""
Trigger re-analysis of a document.
"""
document = (
db.query(Document)
.filter(Document.id == document_id, Document.user_id == user_id)
.first()
)
if not document:
raise NotFoundError("Document", document_id)
# Reset status
document.status = DocumentStatus.PENDING
db.commit()
# Trigger reprocessing
from app.services.queue import enqueue_document_task
enqueue_document_task(str(document.id))
return {"success": True, "message": "Document reanalysis queued"}
def _calculate_document_stats(db: Session, user_id: str) -> dict:
"""Calculate aggregated statistics for user's documents"""
# Category distribution
category_counts = (
db.query(Document.category, func.count(Document.id))
.filter(Document.user_id == user_id, Document.category.isnot(None))
.group_by(Document.category)
.all()
)
by_category = {
cat.value if cat else "other": count for cat, count in category_counts
}
# Status distribution
status_counts = (
db.query(Document.status, func.count(Document.id))
.filter(Document.user_id == user_id)
.group_by(Document.status)
.all()
)
by_status = {
status.value if status else "unknown": count for status, count in status_counts
}
# Average safety score
avg_score = (
db.query(func.avg(Document.safety_score))
.filter(Document.user_id == user_id, Document.safety_score.isnot(None))
.scalar()
)
return {
"by_category": by_category,
"by_status": by_status,
"avg_safety_score": round(avg_score, 2) if avg_score else None,
}
|