feat(findings): Add Django management command to populate database with dummy data (#7049)

This commit is contained in:
Víctor Fernández Poyatos
2025-02-26 16:15:37 +01:00
committed by César Arroba
parent 3194675a5c
commit 102d099947
4 changed files with 323 additions and 1 deletions
+63
View File
@@ -269,3 +269,66 @@ poetry shell
cd src/backend
pytest
```
# Custom commands
Django provides a way to create custom commands that can be run from the command line.
> These commands can be found in: ```prowler/api/src/backend/api/management/commands```
To run a custom command, you need to be in the `prowler/api/src/backend` directory and run:
```console
poetry shell
python manage.py <command_name>
```
## Generate dummy data
```console
python manage.py findings --tenant
<TENANT_ID> --findings <NUM_FINDINGS> --re
sources <NUM_RESOURCES> --batch <TRANSACTION_BATCH_SIZE> --alias <ALIAS>
```
This command creates, for a given tenant, a provider, scan and a set of findings and resources related altogether.
> Scan progress and state are updated in real time.
> - 0-33%: Create resources.
> - 33-66%: Create findings.
> - 66%: Create resource-finding mapping.
>
> The last step is required to access the findings details, since the UI needs that to print all the information.
### Example
```console
~/backend $ poetry run python manage.py findings --tenant
fffb1893-3fc7-4623-a5d9-fae47da1c528 --findings 25000 --re
sources 1000 --batch 5000 --alias test-script
Starting data population
Tenant: fffb1893-3fc7-4623-a5d9-fae47da1c528
Alias: test-script
Resources: 1000
Findings: 25000
Batch size: 5000
Creating resources...
100%|███████████████████████| 1/1 [00:00<00:00, 7.72it/s]
Resources created successfully.
Creating findings...
100%|███████████████████████| 5/5 [00:05<00:00, 1.09s/it]
Findings created successfully.
Creating resource-finding mappings...
100%|███████████████████████| 5/5 [00:02<00:00, 1.81it/s]
Resource-finding mappings created successfully.
Successfully populated test data.
```
+22 -1
View File
@@ -4776,6 +4776,27 @@ files = [
{file = "tomlkit-0.13.2.tar.gz", hash = "sha256:fff5fe59a87295b278abd31bec92c15d9bc4a06885ab12bcea52c71119392e79"},
]
[[package]]
name = "tqdm"
version = "4.67.1"
description = "Fast, Extensible Progress Meter"
optional = false
python-versions = ">=3.7"
files = [
{file = "tqdm-4.67.1-py3-none-any.whl", hash = "sha256:26445eca388f82e72884e0d580d5464cd801a3ea01e63e5601bdff9ba6a48de2"},
{file = "tqdm-4.67.1.tar.gz", hash = "sha256:f8aef9c52c08c13a65f30ea34f4e5aac3fd1a34959879d7e59e63027286627f2"},
]
[package.dependencies]
colorama = {version = "*", markers = "platform_system == \"Windows\""}
[package.extras]
dev = ["nbval", "pytest (>=6)", "pytest-asyncio (>=0.24)", "pytest-cov", "pytest-timeout"]
discord = ["requests"]
notebook = ["ipywidgets (>=6)"]
slack = ["slack-sdk"]
telegram = ["requests"]
[[package]]
name = "typer"
version = "0.15.1"
@@ -5154,4 +5175,4 @@ type = ["pytest-mypy"]
[metadata]
lock-version = "2.0"
python-versions = ">=3.11,<3.13"
content-hash = "a8927a21c9e3006f5378b4bdf72108e0d45c2d803d59733f9824b3eaf12ff5e1"
content-hash = "3360123df5b0ad1fb39f186b801c3554fbaeea06f32765b8a32a2bb7eb87b41b"
+1
View File
@@ -52,6 +52,7 @@ pytest-randomly = "3.15.0"
pytest-xdist = "3.6.1"
ruff = "0.5.0"
safety = "3.2.9"
tqdm = "4.67.1"
vulture = "2.14"
[tool.poetry.scripts]
@@ -0,0 +1,237 @@
import random
from datetime import datetime, timezone
from math import ceil
from uuid import uuid4
from django.core.management.base import BaseCommand
from tqdm import tqdm
from api.db_utils import rls_transaction
from api.models import (
Finding,
Provider,
Resource,
ResourceFindingMapping,
Scan,
StatusChoices,
)
from prowler.lib.check.models import CheckMetadata
class Command(BaseCommand):
help = "Populates the database with test data for performance testing."
def add_arguments(self, parser):
parser.add_argument(
"--tenant",
type=str,
required=True,
help="Tenant id for which the data will be populated.",
)
parser.add_argument(
"--resources",
type=int,
required=True,
help="The number of resources to create.",
)
parser.add_argument(
"--findings",
type=int,
required=True,
help="The number of findings to create.",
)
parser.add_argument(
"--batch", type=int, required=True, help="The batch size for bulk creation."
)
parser.add_argument(
"--alias",
type=str,
required=False,
help="Optional alias for the provider and scan",
)
def handle(self, *args, **options):
tenant_id = options["tenant"]
num_resources = options["resources"]
num_findings = options["findings"]
batch_size = options["batch"]
alias = options["alias"] or "Testing"
uid_token = str(uuid4())
self.stdout.write(self.style.NOTICE("Starting data population"))
self.stdout.write(self.style.NOTICE(f"\tTenant: {tenant_id}"))
self.stdout.write(self.style.NOTICE(f"\tAlias: {alias}"))
self.stdout.write(self.style.NOTICE(f"\tResources: {num_resources}"))
self.stdout.write(self.style.NOTICE(f"\tFindings: {num_findings}"))
self.stdout.write(self.style.NOTICE(f"\tBatch size: {batch_size}\n\n"))
# Resource metadata
possible_regions = [
"us-east-1",
"us-east-2",
"us-west-1",
"us-west-2",
"ca-central-1",
"eu-central-1",
"eu-west-1",
"eu-west-2",
"eu-west-3",
"ap-southeast-1",
"ap-southeast-2",
"ap-northeast-1",
"ap-northeast-2",
"ap-south-1",
"sa-east-1",
]
possible_services = []
possible_types = []
bulk_check_metadata = CheckMetadata.get_bulk(provider="aws")
for check_metadata in bulk_check_metadata.values():
if check_metadata.ServiceName not in possible_services:
possible_services.append(check_metadata.ServiceName)
if (
check_metadata.ResourceType
and check_metadata.ResourceType not in possible_types
):
possible_types.append(check_metadata.ResourceType)
with rls_transaction(tenant_id):
provider, _ = Provider.all_objects.get_or_create(
tenant_id=tenant_id,
provider="aws",
connected=True,
uid=str(random.randint(100000000000, 999999999999)),
defaults={
"alias": alias,
},
)
with rls_transaction(tenant_id):
scan = Scan.all_objects.create(
tenant_id=tenant_id,
provider=provider,
name=alias,
trigger="manual",
state="executing",
progress=0,
started_at=datetime.now(timezone.utc),
)
scan_state = "completed"
try:
# Create resources
resources = []
for i in range(num_resources):
resources.append(
Resource(
tenant_id=tenant_id,
provider_id=provider.id,
uid=f"testing-{uid_token}-{i}",
name=f"Testing {uid_token}-{i}",
region=random.choice(possible_regions),
service=random.choice(possible_services),
type=random.choice(possible_types),
)
)
num_batches = ceil(len(resources) / batch_size)
self.stdout.write(self.style.WARNING("Creating resources..."))
for i in tqdm(range(0, len(resources), batch_size), total=num_batches):
with rls_transaction(tenant_id):
Resource.all_objects.bulk_create(resources[i : i + batch_size])
self.stdout.write(self.style.SUCCESS("Resources created successfully.\n\n"))
with rls_transaction(tenant_id):
scan.progress = 33
scan.save()
# Create Findings
findings = []
possible_deltas = ["new", "changed", None]
possible_severities = ["critical", "high", "medium", "low"]
findings_resources_mapping = []
for i in range(num_findings):
severity = random.choice(possible_severities)
check_id = random.randint(1, 1000)
assigned_resource_num = random.randint(0, len(resources) - 1)
assigned_resource = resources[assigned_resource_num]
findings_resources_mapping.append(assigned_resource_num)
findings.append(
Finding(
tenant_id=tenant_id,
scan=scan,
uid=f"testing-{uid_token}-{i}",
delta=random.choice(possible_deltas),
check_id=f"check-{check_id}",
status=random.choice(list(StatusChoices)),
severity=severity,
impact=severity,
raw_result={},
check_metadata={
"checktitle": f"Test title for check {check_id}",
"risk": f"Testing risk {uid_token}-{i}",
"provider": "aws",
"severity": severity,
"categories": ["category1", "category2", "category3"],
"description": "This is a random description that should not matter for testing purposes.",
"servicename": assigned_resource.service,
"resourcetype": assigned_resource.type,
},
)
)
num_batches = ceil(len(findings) / batch_size)
self.stdout.write(self.style.WARNING("Creating findings..."))
for i in tqdm(range(0, len(findings), batch_size), total=num_batches):
with rls_transaction(tenant_id):
Finding.all_objects.bulk_create(findings[i : i + batch_size])
self.stdout.write(self.style.SUCCESS("Findings created successfully.\n\n"))
with rls_transaction(tenant_id):
scan.progress = 66
scan.save()
# Create ResourceFindingMapping
mappings = []
for index, f in enumerate(findings):
mappings.append(
ResourceFindingMapping(
tenant_id=tenant_id,
resource=resources[findings_resources_mapping[index]],
finding=f,
)
)
num_batches = ceil(len(mappings) / batch_size)
self.stdout.write(
self.style.WARNING("Creating resource-finding mappings...")
)
for i in tqdm(range(0, len(mappings), batch_size), total=num_batches):
with rls_transaction(tenant_id):
ResourceFindingMapping.objects.bulk_create(
mappings[i : i + batch_size]
)
self.stdout.write(
self.style.SUCCESS(
"Resource-finding mappings created successfully.\n\n"
)
)
except Exception as e:
self.stdout.write(self.style.ERROR(f"Failed to populate test data: {e}"))
scan_state = "failed"
finally:
scan.completed_at = datetime.now(timezone.utc)
scan.duration = int(
(datetime.now(timezone.utc) - scan.started_at).total_seconds()
)
scan.progress = 100
scan.state = scan_state
scan.unique_resource_count = num_resources
with rls_transaction(tenant_id):
scan.save()
self.stdout.write(self.style.NOTICE("Successfully populated test data."))