Compare commits

...

1 Commits

Author SHA1 Message Date
Josema Camacho
ccf0967033 refactor(api): remove dead cleanup_findings no-op from attack-paths module 2026-04-14 15:27:07 +02:00
5 changed files with 3 additions and 56 deletions

View File

@@ -7,6 +7,7 @@ All notable changes to the **Prowler API** are documented in this file.
### 🔄 Changed
- Bump Poetry to `2.3.4` in Dockerfile and pre-commit hooks. Regenerate `api/poetry.lock` [(#10681)](https://github.com/prowler-cloud/prowler/pull/10681)
- Attack Paths: Remove dead `cleanup_findings` no-op and its supporting `prowler_finding_lastupdated` index [(#10684)](https://github.com/prowler-cloud/prowler/pull/10684)
### 🔐 Security

View File

@@ -5,7 +5,6 @@ This module handles:
- Adding resource labels to Cartography nodes for efficient lookups
- Loading Prowler findings into the graph
- Linking findings to resources
- Cleaning up stale findings
"""
from collections import defaultdict
@@ -24,7 +23,6 @@ from tasks.jobs.attack_paths.config import (
)
from tasks.jobs.attack_paths.queries import (
ADD_RESOURCE_LABEL_TEMPLATE,
CLEANUP_FINDINGS_TEMPLATE,
INSERT_FINDING_TEMPLATE,
render_cypher_template,
)
@@ -92,14 +90,13 @@ def analysis(
"""
Main entry point for Prowler findings analysis.
Adds resource labels, loads findings, and cleans up stale data.
Adds resource labels and loads findings.
"""
add_resource_label(
neo4j_session, prowler_api_provider.provider, str(prowler_api_provider.uid)
)
findings_data = stream_findings_with_resources(prowler_api_provider, scan_id)
load_findings(neo4j_session, findings_data, prowler_api_provider, config)
cleanup_findings(neo4j_session, prowler_api_provider, config)
def add_resource_label(
@@ -183,28 +180,6 @@ def load_findings(
logger.info(f"Finished loading {total_records} records in {batch_num} batches")
def cleanup_findings(
neo4j_session: neo4j.Session,
prowler_api_provider: Provider,
config: CartographyConfig,
) -> None:
"""Remove stale findings (classic Cartography behaviour)."""
parameters = {
"last_updated": config.update_tag,
"batch_size": BATCH_SIZE,
}
batch = 1
deleted_count = 1
while deleted_count > 0:
logger.info(f"Cleaning findings batch {batch}")
result = neo4j_session.run(CLEANUP_FINDINGS_TEMPLATE, parameters)
deleted_count = result.single().get("deleted_findings_count", 0)
batch += 1
# Findings Streaming (Generator-based)
# -------------------------------------

View File

@@ -13,14 +13,13 @@ from tasks.jobs.attack_paths.config import (
logger = get_task_logger(__name__)
# Indexes for Prowler findings and resource lookups
# Indexes for Prowler Findings and resource lookups
FINDINGS_INDEX_STATEMENTS = [
# Resource indexes for Prowler Finding lookups
"CREATE INDEX aws_resource_arn IF NOT EXISTS FOR (n:_AWSResource) ON (n.arn);",
"CREATE INDEX aws_resource_id IF NOT EXISTS FOR (n:_AWSResource) ON (n.id);",
# Prowler Finding indexes
f"CREATE INDEX prowler_finding_id IF NOT EXISTS FOR (n:{PROWLER_FINDING_LABEL}) ON (n.id);",
f"CREATE INDEX prowler_finding_lastupdated IF NOT EXISTS FOR (n:{PROWLER_FINDING_LABEL}) ON (n.lastupdated);",
f"CREATE INDEX prowler_finding_status IF NOT EXISTS FOR (n:{PROWLER_FINDING_LABEL}) ON (n.status);",
# Internet node index for MERGE lookups
f"CREATE INDEX internet_id IF NOT EXISTS FOR (n:{INTERNET_NODE_LABEL}) ON (n.id);",

View File

@@ -80,17 +80,6 @@ INSERT_FINDING_TEMPLATE = f"""
rel.lastupdated = $last_updated
"""
CLEANUP_FINDINGS_TEMPLATE = f"""
MATCH (finding:{PROWLER_FINDING_LABEL})
WHERE finding.lastupdated < $last_updated
WITH finding LIMIT $batch_size
DETACH DELETE finding
RETURN COUNT(finding) AS deleted_findings_count
"""
# Internet queries (used by internet.py)
# ---------------------------------------

View File

@@ -1298,23 +1298,6 @@ class TestAttackPathsFindingsHelpers:
assert params["last_updated"] == config.update_tag
assert "findings_data" in params
def test_cleanup_findings_runs_batches(self, providers_fixture):
provider = providers_fixture[0]
config = SimpleNamespace(update_tag=1024)
mock_session = MagicMock()
first_batch = MagicMock()
first_batch.single.return_value = {"deleted_findings_count": 3}
second_batch = MagicMock()
second_batch.single.return_value = {"deleted_findings_count": 0}
mock_session.run.side_effect = [first_batch, second_batch]
findings_module.cleanup_findings(mock_session, provider, config)
assert mock_session.run.call_count == 2
params = mock_session.run.call_args.args[1]
assert params["last_updated"] == config.update_tag
def test_stream_findings_with_resources_returns_latest_scan_data(
self,
tenants_fixture,