cartography 0.106.0rc2__py3-none-any.whl → 0.107.0rc2__py3-none-any.whl

cartography/intel/airbyte/sources.py

@@ -0,0 +1,78 @@
+import logging
+from typing import Any
+from typing import Dict
+from typing import List
+
+import neo4j
+
+from cartography.client.core.tx import load
+from cartography.graph.job import GraphJob
+from cartography.intel.airbyte.util import AirbyteClient
+from cartography.intel.airbyte.util import normalize_airbyte_config
+from cartography.models.airbyte.source import AirbyteSourceSchema
+from cartography.util import timeit
+
+logger = logging.getLogger(__name__)
+
+
+@timeit
+def sync(
+    neo4j_session: neo4j.Session,
+    api_session: AirbyteClient,
+    org_id: str,
+    workspace_ids: List[str],
+    common_job_parameters: Dict[str, Any],
+) -> None:
+    sources = get(api_session, workspace_ids)
+    transformed_sources = transform(sources)
+    load_sources(
+        neo4j_session, transformed_sources, org_id, common_job_parameters["UPDATE_TAG"]
+    )
+    cleanup(neo4j_session, common_job_parameters)
+
+
+@timeit
+def get(
+    api_session: AirbyteClient,
+    workspace_ids: List[str],
+) -> List[Dict[str, Any]]:
+    return api_session.get(
+        "/sources",
+        params={"workspaceIds": ",".join(workspace_ids)} if workspace_ids else None,
+    )
+
+
+def transform(sources: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
+    transformed_sources = []
+    for source in sources:
+        source["configuration"] = normalize_airbyte_config(
+            source.get("configuration", {})
+        )
+        transformed_sources.append(source)
+    return transformed_sources
+
+
+@timeit
+def load_sources(
+    neo4j_session: neo4j.Session,
+    data: List[Dict[str, Any]],
+    org_id: str,
+    update_tag: int,
+) -> None:
+    logger.info("Loading %d Airbyte Sources into Neo4j.", len(data))
+    load(
+        neo4j_session,
+        AirbyteSourceSchema(),
+        data,
+        lastupdated=update_tag,
+        ORG_ID=org_id,
+    )
+
+
+@timeit
+def cleanup(
+    neo4j_session: neo4j.Session, common_job_parameters: Dict[str, Any]
+) -> None:
+    GraphJob.from_node_schema(AirbyteSourceSchema(), common_job_parameters).run(
+        neo4j_session
+    )

cartography/intel/airbyte/tags.py

@@ -0,0 +1,64 @@
+import logging
+from typing import Any
+from typing import Dict
+from typing import List
+
+import neo4j
+
+from cartography.client.core.tx import load
+from cartography.graph.job import GraphJob
+from cartography.intel.airbyte.util import AirbyteClient
+from cartography.models.airbyte.tag import AirbyteTagSchema
+from cartography.util import timeit
+
+logger = logging.getLogger(__name__)
+
+
+@timeit
+def sync(
+    neo4j_session: neo4j.Session,
+    api_session: AirbyteClient,
+    org_id: str,
+    workspace_ids: List[str],
+    common_job_parameters: Dict[str, Any],
+) -> None:
+    tags = get(api_session, workspace_ids)
+    load_tags(neo4j_session, tags, org_id, common_job_parameters["UPDATE_TAG"])
+    cleanup(neo4j_session, common_job_parameters)
+
+
+@timeit
+def get(
+    api_session: AirbyteClient,
+    workspace_ids: List[str],
+) -> List[Dict[str, Any]]:
+    return api_session.get(
+        "/tags",
+        params={"workspaceIds": ",".join(workspace_ids)} if workspace_ids else None,
+    )
+
+
+@timeit
+def load_tags(
+    neo4j_session: neo4j.Session,
+    data: List[Dict[str, Any]],
+    org_id: str,
+    update_tag: int,
+) -> None:
+    logger.info("Loading %d Airbyte Tags into Neo4j.", len(data))
+    load(
+        neo4j_session,
+        AirbyteTagSchema(),
+        data,
+        lastupdated=update_tag,
+        ORG_ID=org_id,
+    )
+
+
+@timeit
+def cleanup(
+    neo4j_session: neo4j.Session, common_job_parameters: Dict[str, Any]
+) -> None:
+    GraphJob.from_node_schema(AirbyteTagSchema(), common_job_parameters).run(
+        neo4j_session
+    )

cartography/intel/airbyte/users.py

@@ -0,0 +1,106 @@
+import logging
+from typing import Any
+from typing import Dict
+from typing import List
+from typing import Tuple
+
+import neo4j
+
+from cartography.client.core.tx import load
+from cartography.graph.job import GraphJob
+from cartography.intel.airbyte.util import AirbyteClient
+from cartography.models.airbyte.user import AirbyteUserSchema
+from cartography.util import timeit
+
+logger = logging.getLogger(__name__)
+
+
+@timeit
+def sync(
+    neo4j_session: neo4j.Session,
+    api_session: AirbyteClient,
+    org_id: str,
+    common_job_parameters: Dict[str, Any],
+) -> None:
+    users = get(api_session, org_id=org_id)
+    for user in users:
+        permissions = get_permissions(api_session, user["id"], org_id=org_id)
+        org_admin, workspace_admin, workspace_member = transform_permissions(
+            permissions
+        )
+        user["adminOfOrganization"] = org_admin
+        user["adminOfWorkspace"] = workspace_admin
+        user["memberOfWorkspace"] = workspace_member
+    load_users(neo4j_session, users, org_id, common_job_parameters["UPDATE_TAG"])
+    cleanup(neo4j_session, common_job_parameters)
+
+
+@timeit
+def get(
+    api_session: AirbyteClient,
+    org_id: str,
+) -> List[Dict[str, Any]]:
+    return api_session.get("/users", params={"organizationId": org_id})
+
+
+@timeit
+def get_permissions(
+    api_session: AirbyteClient,
+    user_id: str,
+    org_id: str,
+) -> List[Dict[str, Any]]:
+    return api_session.get(
+        "/permissions",
+        params={"organizationId": org_id, "userId": user_id},
+    )
+
+
+@timeit
+def transform_permissions(
+    permissions: List[Dict[str, Any]],
+) -> Tuple[
+    List[str],  # org_admin
+    List[str],  # workspace_admin
+    List[str],  # workspace_member
+]:
+    org_admin: list[str] = []
+    workspace_admin: list[str] = []
+    workspace_member: list[str] = []
+
+    for permission in permissions:
+        # workspace
+        if permission["scope"] == "workspace":
+            if permission["permissionType"] in ("workspace_owner", "workspace_admin"):
+                workspace_admin.append(permission["scopeId"])
+            workspace_member.append(permission["scopeId"])
+        # organization
+        elif permission["scope"] == "organization":
+            if permission["permissionType"] in ("organization_admin",):
+                org_admin.append(permission["scopeId"])
+    return org_admin, workspace_admin, workspace_member
+
+
+@timeit
+def load_users(
+    neo4j_session: neo4j.Session,
+    data: List[Dict[str, Any]],
+    org_id: str,
+    update_tag: int,
+) -> None:
+    logger.info("Loading %d Airbyte Users into Neo4j.", len(data))
+    load(
+        neo4j_session,
+        AirbyteUserSchema(),
+        data,
+        ORG_ID=org_id,
+        lastupdated=update_tag,
+    )
+
+
+@timeit
+def cleanup(
+    neo4j_session: neo4j.Session, common_job_parameters: Dict[str, Any]
+) -> None:
+    GraphJob.from_node_schema(AirbyteUserSchema(), common_job_parameters).run(
+        neo4j_session
+    )

cartography/intel/airbyte/util.py

@@ -0,0 +1,122 @@
+import logging
+import time
+from typing import Any
+
+import requests
+
+logger = logging.getLogger(__name__)
+# Connect and read timeouts of 60 seconds each; see https://requests.readthedocs.io/en/master/user/advanced/#timeouts
+_TIMEOUT = (60, 60)
+
+
+class AirbyteClient:
+    """A client for interacting with the Airbyte API.
+    This client handles authentication and provides methods to make GET requests to the Airbyte API.
+    It automatically handles pagination for GET requests that return multiple pages of data.
+    """
+
+    def __init__(self, base_url: str, client_id: str, client_secret: str) -> None:
+        self._client_id = client_id
+        self._client_secret = client_secret
+        self.base_url = base_url
+        self._access_token_expiry: int | None = None
+        self._session = requests.Session()
+
+    def get(self, uri: str, params: dict | None = None, offset: int = 0) -> list[dict]:
+        """Make a GET request to the Airbyte API.
+        This method handles authentication and pagination.
+        Args:
+            uri (str): The URI to make the GET request to.
+            params (dict | None): Optional parameters to include in the request.
+            offset (int): The offset for pagination, defaults to 0.
+        Returns:
+            list[dict]: A list of dictionaries containing the data from the response.
+        """
+        self.authenticate()
+        if params is None:
+            params_with_pagination = {}
+        else:
+            params_with_pagination = params.copy()
+        params_with_pagination["offset"] = offset
+        response = self._session.get(
+            f"{self.base_url}{uri}", params=params_with_pagination, timeout=_TIMEOUT
+        )
+        response.raise_for_status()
+        data = response.json().get("data")
+        if response.json().get("next", "") != "":
+            data.extend(
+                self.get(
+                    uri,
+                    params=params,
+                    offset=offset + len(data),
+                )
+            )
+        return data
+
+    def authenticate(self) -> None:
+        """Authenticate with the Airbyte API using client credentials.
+        This method checks if the access token is still valid and renews it if necessary.
+        If the access token is expired or not set, it will make a request to obtain a new access token.
+        """
+        if self._access_token_expiry and self._access_token_expiry >= time.time():
+            return
+        self._session.headers.pop("Authorization", None)
+        payload = {
+            "grant-type": "client_credentials",
+            "client_id": self._client_id,
+            "client_secret": self._client_secret,
+        }
+        response = self._session.post(
+            f"{self.base_url}/applications/token", json=payload, timeout=_TIMEOUT
+        )
+        response.raise_for_status()
+        data = response.json()
+        self._session.headers["Authorization"] = (
+            f"Bearer {data.get('access_token', '')}"
+        )
+        token_expiry = data.get("expires_in", 0)
+        self._access_token_expiry = time.time() + token_expiry
+        logger.debug("Access token renewed, expires in %s seconds.", token_expiry)
+
+
+def normalize_airbyte_config(config: dict[str, Any]) -> dict[str, Any]:
+    """Normalize the Airbyte configuration dictionary.
+    This function takes a configuration dictionary and normalizes it by mapping keys to a standard set of keys.
+    This is useful for ensuring consistency across different configurations, and will allow to connect to existing nodes.
+    Args:
+        config (dict[str, Any]): The configuration dictionary to normalize.
+    Returns:
+        dict[str, Any]: A normalized configuration dictionary with standardized keys.
+    """
+    normalized_config = {}
+    for key in config:
+        if key in ("host", "port", "name", "region", "endpoint", "account", ""):
+            normalized_config[key] = config[key]
+        elif key in ("aws_region_name", "region_name", "s3_bucket_region"):
+            normalized_config["region"] = config[key]
+        elif key in ("queue_url", "url", "s3_endpoint"):
+            normalized_config["endpoint"] = config[key]
+        elif key in ("azure_blob_storage_account_name", "storage_account_name"):
+            normalized_config["account"] = config[key]
+        elif key in (
+            "azure_blob_storage_container_name",
+            "bucket",
+            "database",
+            "s3_bucket_name",
+        ):
+            normalized_config["name"] = config[key]
+    return normalized_config
+
+
+def list_to_string(lst: list[str]) -> str | None:
+    """Convert a list of strings to a comma-separated string."""
+    if len(lst) == 0:
+        return None
+    # Sublist
+    formated_list: list[str] = []
+    for item in lst:
+        if isinstance(item, list):
+            formated_list.append("|".join(item))
+        else:
+            formated_list.append(str(item))
+    return ",".join(formated_list)

cartography/intel/airbyte/workspaces.py

@@ -0,0 +1,63 @@
+import logging
+from typing import Any
+from typing import Dict
+from typing import List
+
+import neo4j
+
+from cartography.client.core.tx import load
+from cartography.graph.job import GraphJob
+from cartography.intel.airbyte.util import AirbyteClient
+from cartography.models.airbyte.workspace import AirbyteWorkspaceSchema
+from cartography.util import timeit
+
+logger = logging.getLogger(__name__)
+
+
+@timeit
+def sync(
+    neo4j_session: neo4j.Session,
+    api_session: AirbyteClient,
+    org_id: str,
+    common_job_parameters: Dict[str, Any],
+) -> List[Dict[str, Any]]:
+    workspaces = get(api_session, org_id)
+    load_workspaces(
+        neo4j_session, workspaces, org_id, common_job_parameters["UPDATE_TAG"]
+    )
+    cleanup(neo4j_session, common_job_parameters)
+    return workspaces
+
+
+@timeit
+def get(
+    api_session: AirbyteClient,
+    org_id: str,
+) -> List[Dict[str, Any]]:
+    return api_session.get("/workspaces", params={"organizationId": org_id})
+
+
+@timeit
+def load_workspaces(
+    neo4j_session: neo4j.Session,
+    data: List[Dict[str, Any]],
+    org_id: str,
+    update_tag: int,
+) -> None:
+    logger.info("Loading %d Airbyte Workspaces into Neo4j.", len(data))
+    load(
+        neo4j_session,
+        AirbyteWorkspaceSchema(),
+        data,
+        lastupdated=update_tag,
+        ORG_ID=org_id,
+    )
+
+
+@timeit
+def cleanup(
+    neo4j_session: neo4j.Session, common_job_parameters: Dict[str, Any]
+) -> None:
+    GraphJob.from_node_schema(AirbyteWorkspaceSchema(), common_job_parameters).run(
+        neo4j_session
+    )

cartography/intel/aws/__init__.py

@@ -310,6 +310,7 @@ def start_aws_ingestion(neo4j_session: neo4j.Session, config: Config) -> None:
     common_job_parameters = {
         "UPDATE_TAG": config.update_tag,
         "permission_relationships_file": config.permission_relationships_file,
+        "aws_cloudtrail_management_events_lookback_hours": config.aws_cloudtrail_management_events_lookback_hours,
     }
     try:
         boto3_session = boto3.Session()