Files
leocrm/app/routes/import_export.py
T

372 lines
12 KiB
Python
Raw Normal View History

"""Import/export routes — CSV/JSON/XLSX import, preview, validate, background jobs, CSV/XLSX export."""
from __future__ import annotations
import io
import json
import uuid
from fastapi import (
APIRouter,
Depends,
File,
Form,
HTTPException,
Query,
UploadFile,
)
from sqlalchemy.ext.asyncio import AsyncSession
from starlette.responses import StreamingResponse
from app.core.db import get_db
from app.deps import require_permission
from app.services import import_export_service
from app.services.import_export_helpers import (
parse_file,
write_xlsx,
)
router = APIRouter(prefix="/api/v1", tags=["import_export"])
# Row threshold for background job processing
_BACKGROUND_THRESHOLD = 1000
@router.post("/import")
async def import_csv(
file: UploadFile = File(...),
entity_type: str = Form(...),
field_mapping: str = Form(None),
db: AsyncSession = Depends(get_db),
current_user: dict = Depends(require_permission("import_export:write")),
):
"""Import companies or contacts from CSV/JSON/XLSX file.
entity_type: 'companies' or 'contacts'.
field_mapping: Optional JSON string of source_column -> target_field mapping.
For files > 1000 rows, the import runs as a background ARQ job.
"""
tenant_id = uuid.UUID(current_user["tenant_id"])
user_id = uuid.UUID(current_user["user_id"])
content = await file.read()
csv_content = content.decode("utf-8", errors="replace")
# Parse mapping if provided
mapping = None
if field_mapping:
try:
mapping = json.loads(field_mapping)
except json.JSONDecodeError:
raise HTTPException(status_code=400, detail="Invalid field_mapping JSON") from None
# Check row count for background processing
try:
rows = parse_file(file.filename or "upload.csv", content)
except Exception as exc:
raise HTTPException(status_code=400, detail=f"Failed to parse file: {exc}") from exc
if len(rows) > _BACKGROUND_THRESHOLD:
# Enqueue as background job
from app.services.import_export_jobs import create_import_job
try:
job_id = await create_import_job(
entity_type=entity_type,
csv_content=csv_content,
tenant_id=tenant_id,
user_id=user_id,
field_mapping=mapping,
)
return {
"status": "pending",
"job_id": job_id,
"message": f"Import enqueued as background job ({len(rows)} rows)",
"total": len(rows),
}
except Exception as exc:
raise HTTPException(status_code=500, detail=f"Failed to enqueue import job: {exc}") from exc
# Synchronous import for smaller files
result = await import_export_service.import_csv(
db,
tenant_id,
user_id,
csv_content,
entity_type=entity_type,
dry_run=False,
field_mapping=mapping,
)
return result
@router.post("/import/preview")
async def import_csv_preview(
file: UploadFile = File(...),
entity_type: str = Form(...),
current_user: dict = Depends(require_permission("import_export:read")),
):
"""Preview CSV import (dry-run — no DB changes).
Returns first 10 rows, detected columns, and mapping suggestion.
"""
content = await file.read()
try:
result = import_export_service.preview_import(
filename=file.filename or "upload.csv",
content=content,
entity_type=entity_type,
)
except Exception as exc:
raise HTTPException(status_code=400, detail=f"Failed to parse file: {exc}") from exc
return result
@router.post("/import/validate")
async def import_validate(
file: UploadFile = File(...),
entity_type: str = Form(...),
field_mapping: str = Form(None),
current_user: dict = Depends(require_permission("import_export:read")),
):
"""Validate all rows against mapping and return error report without importing."""
content = await file.read()
mapping = None
if field_mapping:
try:
mapping = json.loads(field_mapping)
except json.JSONDecodeError:
raise HTTPException(status_code=400, detail="Invalid field_mapping JSON") from None
try:
result = import_export_service.validate_import(
filename=file.filename or "upload.csv",
content=content,
entity_type=entity_type,
field_mapping=mapping,
)
except Exception as exc:
raise HTTPException(status_code=400, detail=f"Failed to validate file: {exc}") from exc
return result
@router.get("/import/status/{job_id}")
async def import_job_status(
job_id: str,
current_user: dict = Depends(require_permission("import_export:read")),
):
"""Get status of a background import job."""
from app.services.import_export_jobs import get_import_job_status
status = await get_import_job_status(job_id)
if status is None:
raise HTTPException(status_code=404, detail=f"Job {job_id} not found")
return status
@router.post("/import/contacts")
async def import_contacts_route(
file: UploadFile = File(...),
field_mapping: str = Form(None),
db: AsyncSession = Depends(get_db),
current_user: dict = Depends(require_permission("import_export:write")),
):
"""Import contacts from CSV/JSON/XLSX file.
For files > 1000 rows, runs as background ARQ job.
"""
tenant_id = uuid.UUID(current_user["tenant_id"])
user_id = uuid.UUID(current_user["user_id"])
content = await file.read()
csv_content = content.decode("utf-8", errors="replace")
mapping = None
if field_mapping:
try:
mapping = json.loads(field_mapping)
except json.JSONDecodeError:
raise HTTPException(status_code=400, detail="Invalid field_mapping JSON") from None
# Check row count for background processing
try:
rows = parse_file(file.filename or "upload.csv", content)
except Exception as exc:
raise HTTPException(status_code=400, detail=f"Failed to parse file: {exc}") from exc
if len(rows) > _BACKGROUND_THRESHOLD:
from app.services.import_export_jobs import create_import_job
try:
job_id = await create_import_job(
entity_type="contacts",
csv_content=csv_content,
tenant_id=tenant_id,
user_id=user_id,
field_mapping=mapping,
)
return {
"status": "pending",
"job_id": job_id,
"message": f"Import enqueued as background job ({len(rows)} rows)",
"total": len(rows),
}
except Exception as exc:
raise HTTPException(status_code=500, detail=f"Failed to enqueue import job: {exc}") from exc
result = await import_export_service.import_contacts(
db,
tenant_id,
user_id,
csv_content,
dry_run=False,
field_mapping=mapping,
)
return result
@router.post("/import/companies")
async def import_companies_route(
file: UploadFile = File(...),
field_mapping: str = Form(None),
db: AsyncSession = Depends(get_db),
current_user: dict = Depends(require_permission("import_export:write")),
):
"""Import companies from CSV/JSON/XLSX file.
For files > 1000 rows, runs as background ARQ job.
"""
tenant_id = uuid.UUID(current_user["tenant_id"])
user_id = uuid.UUID(current_user["user_id"])
content = await file.read()
csv_content = content.decode("utf-8", errors="replace")
mapping = None
if field_mapping:
try:
mapping = json.loads(field_mapping)
except json.JSONDecodeError:
raise HTTPException(status_code=400, detail="Invalid field_mapping JSON") from None
# Check row count for background processing
try:
rows = parse_file(file.filename or "upload.csv", content)
except Exception as exc:
raise HTTPException(status_code=400, detail=f"Failed to parse file: {exc}") from exc
if len(rows) > _BACKGROUND_THRESHOLD:
from app.services.import_export_jobs import create_import_job
try:
job_id = await create_import_job(
entity_type="companies",
csv_content=csv_content,
tenant_id=tenant_id,
user_id=user_id,
field_mapping=mapping,
)
return {
"status": "pending",
"job_id": job_id,
"message": f"Import enqueued as background job ({len(rows)} rows)",
"total": len(rows),
}
except Exception as exc:
raise HTTPException(status_code=500, detail=f"Failed to enqueue import job: {exc}") from exc
result = await import_export_service.import_companies(
db,
tenant_id,
user_id,
csv_content,
dry_run=False,
field_mapping=mapping,
)
return result
@router.get("/export")
async def export_data(
entity_type: str = Query("contacts", pattern="^(contacts|companies)$"),
format: str = Query("csv", pattern="^(csv|xlsx|json)$"),
db: AsyncSession = Depends(get_db),
current_user: dict = Depends(require_permission("import_export:read")),
):
"""Export contacts or companies as CSV, XLSX, or JSON file download.
Query params:
- entity_type: 'contacts' or 'companies' (default: contacts)
- format: 'csv', 'xlsx', or 'json' (default: csv)
"""
tenant_id = uuid.UUID(current_user["tenant_id"])
user_id = uuid.UUID(current_user["user_id"])
is_system_admin = current_user.get("is_system_admin", False)
# Fetch data from the appropriate service function
if entity_type == "contacts":
csv_data = await import_export_service.export_contacts_csv(
db, tenant_id, user_id=user_id, is_system_admin=is_system_admin
)
elif entity_type == "companies":
csv_data = await import_export_service.export_companies_csv(
db, tenant_id, user_id=user_id, is_system_admin=is_system_admin
)
else:
raise HTTPException(status_code=400, detail=f"Unsupported entity_type: {entity_type}")
# Parse CSV data back to rows for format conversion
import csv as _csv
reader = _csv.reader(io.StringIO(csv_data))
all_rows = list(reader)
if not all_rows:
raise HTTPException(status_code=404, detail="No data to export")
headers = all_rows[0]
data_rows = [dict(zip(headers, row, strict=False)) for row in all_rows[1:]]
if format == "xlsx":
try:
xlsx_bytes = write_xlsx(data_rows, headers)
xlsx_filename = f"{entity_type}_export.xlsx"
return StreamingResponse(
io.BytesIO(xlsx_bytes),
media_type="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
headers={"Content-Disposition": f'attachment; filename="{xlsx_filename}"'},
)
except ImportError:
# openpyxl not available — fall back to CSV with a warning header
media_type = "text/csv"
headers = {
"Content-Disposition": f'attachment; filename="{entity_type}_export.csv"',
"X-Export-Warning": "openpyxl not installed, falling back to CSV format",
}
return StreamingResponse(
iter([csv_data.encode("utf-8")]),
media_type=media_type,
headers=headers,
)
if format == "json":
from app.services.import_export_helpers import write_json
json_bytes = write_json(data_rows)
json_filename = f"{entity_type}_export.json"
return StreamingResponse(
io.BytesIO(json_bytes),
media_type="application/json",
headers={"Content-Disposition": f'attachment; filename="{json_filename}"'},
)
# Default: CSV format
csv_filename = f"{entity_type}_export.csv"
return StreamingResponse(
iter([csv_data.encode("utf-8")]),
media_type="text/csv",
headers={"Content-Disposition": f'attachment; filename="{csv_filename}"'},
)