regscale-cli 6.27.3.0__py3-none-any.whl → 6.28.0.0__py3-none-any.whl

regscale/integrations/commercial/aws/inventory/__init__.py

@@ -1,10 +1,12 @@
 """AWS resource inventory collection module."""
 
+import logging
 import os
 from typing import Dict, Any, Optional
 
 from regscale.integrations.commercial.aws.inventory.base import BaseCollector
 from regscale.integrations.commercial.aws.inventory.resources.compute import ComputeCollector
+from regscale.integrations.commercial.aws.inventory.resources.config import ConfigCollector
 from regscale.integrations.commercial.aws.inventory.resources.containers import ContainerCollector
 from regscale.integrations.commercial.aws.inventory.resources.database import DatabaseCollector
 from regscale.integrations.commercial.aws.inventory.resources.integration import IntegrationCollector
@@ -12,6 +14,8 @@ from regscale.integrations.commercial.aws.inventory.resources.networking import
 from regscale.integrations.commercial.aws.inventory.resources.security import SecurityCollector
 from regscale.integrations.commercial.aws.inventory.resources.storage import StorageCollector
 
+logger = logging.getLogger("regscale")
+
 
 class AWSInventoryCollector:
     """Collects inventory of AWS resources."""
@@ -19,40 +23,211 @@ class AWSInventoryCollector:
     def __init__(
         self,
         region: str = os.getenv("AWS_REGION", "us-east-1"),
+        profile: Optional[str] = None,
         aws_access_key_id: Optional[str] = None,
         aws_secret_access_key: Optional[str] = None,
         aws_session_token: Optional[str] = None,
+        account_id: Optional[str] = None,
+        tags: Optional[Dict[str, str]] = None,
+        enabled_services: Optional[Dict[str, bool]] = None,
+        collect_findings: bool = True,
     ):
         """
         Initialize the AWS inventory collector.
 
         :param str region: AWS region to collect inventory from
-        :param str aws_access_key_id: Optional AWS access key ID
-        :param str aws_secret_access_key: Optional AWS secret access key
-        :param str aws_session_token: Optional AWS session ID
+        :param str profile: Optional AWS profile name from ~/.aws/credentials
+        :param str aws_access_key_id: Optional AWS access key ID (overrides profile)
+        :param str aws_secret_access_key: Optional AWS secret access key (overrides profile)
+        :param str aws_session_token: Optional AWS session token (overrides profile)
+        :param str account_id: Optional AWS account ID to filter resources
+        :param dict tags: Optional dictionary of tag key-value pairs to filter resources
+        :param dict enabled_services: Optional dictionary of service names to boolean flags for enabling/disabling collection
+        :param bool collect_findings: Whether to collect security findings (GuardDuty, Security Hub, Inspector). Default True.
         """
         import boto3
 
         self.region = region
-        self.session = boto3.Session(
-            aws_access_key_id=aws_access_key_id,
-            aws_secret_access_key=aws_secret_access_key,
-            region_name=region,
-            aws_session_token=aws_session_token,
+        self.account_id = account_id
+        self.tags = tags
+        self.enabled_services = self._get_enabled_services(enabled_services)
+
+        # If explicit credentials are provided, use them; otherwise use profile
+        if aws_access_key_id or aws_secret_access_key:
+            self.session = boto3.Session(
+                aws_access_key_id=aws_access_key_id,
+                aws_secret_access_key=aws_secret_access_key,
+                region_name=region,
+                aws_session_token=aws_session_token,
+            )
+        else:
+            # Use profile or default credential chain
+            self.session = boto3.Session(
+                profile_name=profile,
+                region_name=region,
+            )
+
+        # Initialize collectors based on enabled services
+        compute_config = self.enabled_services.get("compute", {"enabled": True, "services": {}})
+        self.compute = (
+            ComputeCollector(self.session, self.region, account_id, tags, compute_config.get("services", {}))
+            if compute_config.get("enabled", True)
+            else None
+        )
+
+        storage_config = self.enabled_services.get("storage", {"enabled": True, "services": {}})
+        self.storage = (
+            StorageCollector(self.session, self.region, account_id, tags, storage_config.get("services", {}))
+            if storage_config.get("enabled", True)
+            else None
+        )
+
+        database_config = self.enabled_services.get("database", {"enabled": True, "services": {}})
+        self.database = (
+            DatabaseCollector(self.session, self.region, account_id, tags, database_config.get("services", {}))
+            if database_config.get("enabled", True)
+            else None
+        )
+
+        networking_config = self.enabled_services.get("networking", {"enabled": True, "services": {}})
+        self.networking = (
+            NetworkingCollector(self.session, self.region, account_id, tags, networking_config.get("services", {}))
+            if networking_config.get("enabled", True)
+            else None
+        )
+
+        security_config = self.enabled_services.get("security", {"enabled": True, "services": {}})
+        self.security = (
+            SecurityCollector(
+                self.session, self.region, account_id, tags, security_config.get("services", {}), collect_findings
+            )
+            if security_config.get("enabled", True)
+            else None
+        )
+
+        integration_config = self.enabled_services.get("integration", {"enabled": True, "services": {}})
+        self.integration = (
+            IntegrationCollector(self.session, self.region, account_id, tags, integration_config.get("services", {}))
+            if integration_config.get("enabled", True)
+            else None
+        )
+
+        containers_config = self.enabled_services.get("containers", {"enabled": True, "services": {}})
+        self.containers = (
+            ContainerCollector(self.session, self.region, account_id, tags, containers_config.get("services", {}))
+            if containers_config.get("enabled", True)
+            else None
         )
 
-        # Initialize collectors
-        self.compute = ComputeCollector(self.session, self.region)
-        self.storage = StorageCollector(self.session, self.region)
-        self.database = DatabaseCollector(self.session, self.region)
-        self.networking = NetworkingCollector(self.session, self.region)
-        self.security = SecurityCollector(self.session, self.region)
-        self.integration = IntegrationCollector(self.session, self.region)
-        self.containers = ContainerCollector(self.session, self.region)
+        config_config = self.enabled_services.get("config", {"enabled": True, "services": {}})
+        self.config = (
+            ConfigCollector(self.session, self.region, account_id, tags) if config_config.get("enabled", True) else None
+        )
+
+    def _get_enabled_services(self, enabled_services: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
+        """
+        Get enabled services configuration with support for nested structure.
+        Supports both simple (category: bool) and nested (category: {enabled: bool, services: {...}}) formats.
+
+        :param dict enabled_services: Optional dictionary of service names to boolean flags or nested config
+        :return: Dictionary of service configurations
+        :rtype: Dict[str, Any]
+        """
+        # Default all services to enabled with all sub-services enabled
+        default_services = {
+            "compute": {
+                "enabled": True,
+                "services": {"ec2": True, "lambda": True, "ecs": True, "systems_manager": True},
+            },
+            "storage": {"enabled": True, "services": {"s3": True, "ebs": True}},
+            "database": {"enabled": True, "services": {"rds": True, "dynamodb": True}},
+            "networking": {
+                "enabled": True,
+                "services": {
+                    "vpc": True,
+                    "elastic_ips": True,
+                    "load_balancers": True,
+                    "cloudfront": True,
+                    "route53": True,
+                },
+            },
+            "security": {
+                "enabled": True,
+                "services": {
+                    "iam": True,
+                    "kms": True,
+                    "secrets_manager": True,
+                    "waf": True,
+                    "acm": True,
+                    "cloudtrail": True,
+                    "config": True,
+                    "guardduty": True,
+                    "securityhub": True,
+                    "inspector": True,
+                    "audit_manager": True,
+                },
+            },
+            "integration": {
+                "enabled": True,
+                "services": {"api_gateway": True, "sns": True, "sqs": True, "eventbridge": True},
+            },
+            "containers": {"enabled": True, "services": {"ecr": True}},
+            "config": {"enabled": True, "services": {}},
+        }
+
+        # If no config provided, return defaults
+        if enabled_services is None:
+            return default_services
+
+        # Process configuration - support both simple and nested formats
+        merged_config = {}
+        for category, default_value in default_services.items():
+            if category not in enabled_services:
+                # Category not specified, use default
+                merged_config[category] = default_value
+            elif isinstance(enabled_services[category], bool):
+                # Simple format: security: true/false
+                # Convert to nested format with all services matching the category setting
+                merged_config[category] = {
+                    "enabled": enabled_services[category],
+                    "services": {
+                        service: enabled_services[category] for service in default_value.get("services", {}).keys()
+                    },
+                }
+            elif isinstance(enabled_services[category], dict):
+                # Nested format: security: {enabled: true, services: {...}}
+                category_config = enabled_services[category]
+                enabled_flag = category_config.get("enabled", True)
+                provided_services = category_config.get("services", {})
+
+                # Merge provided services with defaults
+                merged_services = default_value.get("services", {}).copy()
+                merged_services.update(provided_services)
+
+                merged_config[category] = {"enabled": enabled_flag, "services": merged_services}
+            else:
+                # Invalid format, use default
+                logger.warning(f"Invalid configuration format for category '{category}', using defaults")
+                merged_config[category] = default_value
+
+        # Log disabled categories and services
+        disabled_categories = [name for name, config in merged_config.items() if not config.get("enabled", True)]
+        if disabled_categories:
+            logger.info(f"AWS inventory collection disabled for categories: {', '.join(disabled_categories)}")
+
+        for category, config in merged_config.items():
+            if config.get("enabled", True):
+                disabled_services = [service for service, enabled in config.get("services", {}).items() if not enabled]
+                if disabled_services:
+                    logger.info(
+                        f"AWS inventory collection disabled for {category} services: {', '.join(disabled_services)}"
+                    )
+
+        return merged_config
 
     def collect_all(self) -> Dict[str, Any]:
         """
-        Collect all AWS resources.
+        Collect all AWS resources from enabled collectors.
 
         :return: Dictionary containing all AWS resource information
         :rtype: Dict[str, Any]
@@ -66,9 +241,15 @@ class AWSInventoryCollector:
             self.security,
             self.integration,
             self.containers,
+            self.config,
         ]
 
-        for collector in collectors:
+        # Filter out None collectors (disabled services)
+        active_collectors = [c for c in collectors if c is not None]
+
+        logger.info(f"Collecting AWS inventory from {len(active_collectors)} enabled service(s)")
+
+        for collector in active_collectors:
             try:
                 resources = collector.collect()
                 inventory.update(resources)
@@ -83,21 +264,41 @@ class AWSInventoryCollector:
 
 def collect_all_inventory(
     region: str = os.getenv("AWS_REGION", "us-east-1"),
+    profile: Optional[str] = None,
     aws_access_key_id: Optional[str] = None,
     aws_secret_access_key: Optional[str] = None,
     aws_session_token: Optional[str] = None,
+    account_id: Optional[str] = None,
+    tags: Optional[Dict[str, str]] = None,
+    enabled_services: Optional[Dict[str, bool]] = None,
+    collect_findings: bool = True,
 ) -> Dict[str, Any]:
     """
     Collect inventory of all AWS resources.
 
     :param str region: AWS region to collect inventory from
-    :param str aws_access_key_id: Optional AWS access key ID
-    :param str aws_secret_access_key: Optional AWS secret access key
-    :param str aws_session_token: Optional AWS session ID
+    :param str profile: Optional AWS profile name from ~/.aws/credentials
+    :param str aws_access_key_id: Optional AWS access key ID (overrides profile)
+    :param str aws_secret_access_key: Optional AWS secret access key (overrides profile)
+    :param str aws_session_token: Optional AWS session token (overrides profile)
+    :param str account_id: Optional AWS account ID to filter resources
+    :param dict tags: Optional dictionary of tag key-value pairs to filter resources
+    :param dict enabled_services: Optional dictionary of service names to boolean flags for enabling/disabling collection
+    :param bool collect_findings: Whether to collect security findings (GuardDuty, Security Hub, Inspector). Default True.
     :return: Dictionary containing all AWS resource information
     :rtype: Dict[str, Any]
     """
-    collector = AWSInventoryCollector(region, aws_access_key_id, aws_secret_access_key, aws_session_token)
+    collector = AWSInventoryCollector(
+        region,
+        profile,
+        aws_access_key_id,
+        aws_secret_access_key,
+        aws_session_token,
+        account_id,
+        tags,
+        enabled_services,
+        collect_findings,
+    )
     return collector.collect_all()
 
 

regscale/integrations/commercial/aws/inventory/base.py

@@ -1,7 +1,7 @@
 """Base classes for AWS resource collection."""
 
 import logging
-from typing import Any, Dict, TYPE_CHECKING
+from typing import Any, Dict, Optional, TYPE_CHECKING
 
 from botocore.exceptions import ClientError
 
@@ -12,17 +12,27 @@ logger = logging.getLogger("regscale")
 
 
 class BaseCollector:
-    """Base class for AWS resource collectors."""
+    """Base class for AWS resource collectors with universal filtering support."""
 
-    def __init__(self, session: "boto3.Session", region: str):
+    def __init__(
+        self,
+        session: "boto3.Session",
+        region: str,
+        account_id: Optional[str] = None,
+        tags: Optional[Dict[str, str]] = None,
+    ):
         """
-        Initialize the base collector.
+        Initialize the base collector with filtering support.
 
         :param boto3.Session session: AWS session to use for API calls
         :param str region: AWS region to collect from
+        :param str account_id: Optional AWS account ID to filter resources
+        :param dict tags: Optional dictionary of tag key-value pairs to filter resources (AND logic)
         """
         self.session = session
         self.region = region
+        self.account_id = account_id
+        self.tags = tags or {}
 
     def _get_client(self, service_name: str) -> Any:
         """
@@ -32,7 +42,99 @@ class BaseCollector:
         :return: Boto3 client for the service
         :rtype: Any
         """
-        return self.session.client(service_name)
+        return self.session.client(service_name, region_name=self.region)
+
+    def _matches_account(self, resource_arn: str) -> bool:
+        """
+        Check if resource belongs to target account.
+
+        :param str resource_arn: AWS Resource ARN
+        :return: True if resource matches account filter or no filter specified
+        :rtype: bool
+
+        ARN format: arn:partition:service:region:account-id:resource
+        """
+        if not self.account_id:
+            return True  # No filter, include all
+
+        try:
+            # ARN format: arn:aws:service:region:account-id:resource-id
+            arn_parts = resource_arn.split(":")
+            if len(arn_parts) >= 5:
+                arn_account = arn_parts[4]
+                match = arn_account == self.account_id
+                if not match:
+                    logger.debug(f"Filtering out resource {resource_arn} - account {arn_account} != {self.account_id}")
+                return match
+        except (IndexError, AttributeError) as e:
+            logger.debug(f"Could not parse account from ARN {resource_arn}: {e}")
+            return True  # Can't parse, include by default
+
+        return True
+
+    def _matches_tags(self, resource_tags: Any) -> bool:
+        """
+        Check if all filter tags match resource tags (AND logic).
+
+        Supports multiple AWS tag formats:
+        - Dict: {'Key': 'Value', ...}
+        - List of dicts: [{'Key': 'k', 'Value': 'v'}, ...]
+        - List of Tags: [{'key': 'k', 'value': 'v'}, ...] (lowercase)
+
+        :param resource_tags: Resource tags in any AWS format
+        :return: True if all filter tags match (or no filter), False otherwise
+        :rtype: bool
+        """
+        if not self.tags:
+            return True  # No filter, include all
+
+        # Normalize tags to dict format
+        normalized_tags = self._normalize_tags(resource_tags)
+
+        # All filter tags must match (AND logic)
+        for key, value in self.tags.items():
+            if normalized_tags.get(key) != value:
+                logger.debug(
+                    f"Resource does not match tag filter: expected {key}={value}, got {normalized_tags.get(key)}"
+                )
+                return False
+
+        return True
+
+    def _normalize_tags(self, tags: Any) -> Dict[str, str]:
+        """
+        Normalize various AWS tag formats to simple dict.
+
+        Handles:
+        - Dict format: {'Key': 'Value'}
+        - List format: [{'Key': 'k', 'Value': 'v'}] (uppercase)
+        - List format: [{'key': 'k', 'value': 'v'}] (lowercase)
+        - None or empty
+
+        :param tags: Tags in any AWS format
+        :return: Normalized dict of tags
+        :rtype: Dict[str, str]
+        """
+        if not tags:
+            return {}
+
+        if isinstance(tags, dict):
+            return tags
+
+        if isinstance(tags, list):
+            result = {}
+            for tag in tags:
+                if isinstance(tag, dict):
+                    # Handle uppercase format (most common)
+                    if "Key" in tag and "Value" in tag:
+                        result[tag["Key"]] = tag["Value"]
+                    # Handle lowercase format
+                    elif "key" in tag and "value" in tag:
+                        result[tag["key"]] = tag["value"]
+            return result
+
+        logger.warning(f"Unexpected tag format: {type(tags)}")
+        return {}
 
     def _handle_error(self, error: Exception, resource_type: str) -> None:
         """