cartography 0.105.0__py3-none-any.whl → 0.106.0__py3-none-any.whl

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/codebuild.py

@@ -0,0 +1,132 @@
+import logging
+from typing import Any
+from typing import Dict
+from typing import List
+
+import boto3
+import neo4j
+
+from cartography.client.core.tx import load
+from cartography.graph.job import GraphJob
+from cartography.intel.aws.ec2.util import get_botocore_config
+from cartography.models.aws.codebuild.project import CodeBuildProjectSchema
+from cartography.util import aws_handle_regions
+from cartography.util import timeit
+
+logger = logging.getLogger(__name__)
+
+
+@timeit
+@aws_handle_regions
+def get_all_codebuild_projects(
+    boto3_session: boto3.Session, region: str
+) -> List[Dict[str, Any]]:
+
+    client = boto3_session.client(
+        "codebuild", region_name=region, config=get_botocore_config()
+    )
+    paginator = client.get_paginator("list_projects")
+
+    all_projects = []
+
+    for page in paginator.paginate():
+        project_names = page.get("projects", [])
+        if not project_names:
+            continue
+
+        # AWS batch_get_projects accepts up to 100 project names per call as per AWS documentation.
+        for i in range(0, len(project_names), 100):
+            batch = project_names[i : i + 100]
+            response = client.batch_get_projects(names=batch)
+            projects = response.get("projects", [])
+            all_projects.extend(projects)
+    return all_projects
+
+
+def transform_codebuild_projects(
+    projects: List[Dict[str, Any]], region: str
+) -> List[Dict[str, Any]]:
+    """
+    Transform CodeBuild project data for ingestion into Neo4j.
+
+    - Includes all environment variable names.
+    - Variables of type 'PLAINTEXT' retain their values.
+    - Other types (e.g., 'PARAMETER_STORE', 'SECRETS_MANAGER') have their values redacted.
+    """
+    transformed_codebuild_projects = []
+    for project in projects:
+        env_vars = project.get("environment", {}).get("environmentVariables", [])
+        env_var_strings = [
+            f"{var.get('name')}={var.get('value') if var.get('type') == 'PLAINTEXT' else '<REDACTED>'}"
+            for var in env_vars
+        ]
+        transformed_project = {
+            "arn": project["arn"],
+            "created": project.get("created"),
+            "environmentVariables": env_var_strings,
+            "sourceType": project.get("source", {}).get("type"),
+            "sourceLocation": project.get("source", {}).get("location"),
+        }
+        transformed_codebuild_projects.append(transformed_project)
+
+    return transformed_codebuild_projects
+
+
+@timeit
+def load_codebuild_projects(
+    neo4j_session: neo4j.Session,
+    data: List[Dict[str, Any]],
+    region: str,
+    current_aws_account_id: str,
+    aws_update_tag: int,
+) -> None:
+    logger.info(
+        f"Loading CodeBuild {len(data)} projects for region '{region}' into graph.",
+    )
+    load(
+        neo4j_session,
+        CodeBuildProjectSchema(),
+        data,
+        lastupdated=aws_update_tag,
+        Region=region,
+        AWS_ID=current_aws_account_id,
+    )
+
+
+@timeit
+def cleanup(
+    neo4j_session: neo4j.Session,
+    common_job_parameters: Dict[str, Any],
+) -> None:
+    logger.debug("Running Efs cleanup job.")
+    GraphJob.from_node_schema(CodeBuildProjectSchema(), common_job_parameters).run(
+        neo4j_session
+    )
+
+
+@timeit
+def sync(
+    neo4j_session: neo4j.Session,
+    boto3_session: boto3.session.Session,
+    regions: List[str],
+    current_aws_account_id: str,
+    update_tag: int,
+    common_job_parameters: Dict[str, Any],
+) -> None:
+    for region in regions:
+        logger.info(
+            f"Syncing CodeBuild for region '{region}' in account '{current_aws_account_id}'.",
+        )
+
+        projects = get_all_codebuild_projects(boto3_session, region)
+        transformed_projects = transform_codebuild_projects(projects, region)
+
+        load_codebuild_projects(
+            neo4j_session,
+            transformed_projects,
+            region,
+            current_aws_account_id,
+            update_tag,
+        )
+
+    cleanup(neo4j_session, common_job_parameters)