PROD-2663: specify dataset on fides pull (#5260)

CHANGELOG.md

@@ -50,6 +50,7 @@ The types of changes are:
 - Adding erasure support for Microsoft Advertising [#5197](https://github.com/ethyca/fides/pull/5197)
 - Implements fuzzy search for identities in Admin-UI Request Manager [#5232](https://github.com/ethyca/fides/pull/5232)
 - New purpose header field for TCF banner [#5246](https://github.com/ethyca/fides/pull/5246)
+- `fides` subcommand `pull` has resource name subcommands that take a `fides_key` argument allowing you to pull only one resource by name and type [#5260](https://github.com/ethyca/fides/pull/5260)
 
 ### Changed
 - Removed unused `username` parameter from the Delighted integration configuration [#5220](https://github.com/ethyca/fides/pull/5220)

pyproject.toml

@@ -41,6 +41,7 @@ module = [
   "cassandra.*",
   "celery.*",
   "citext.*",
+  "click_default_group.*",
   "dask.*",
   "deepdiff.*",
   "defusedxml.ElementTree.*",

requirements.txt

@@ -5,6 +5,7 @@ APScheduler==3.9.1.post1
 asyncpg==0.27.0
 boto3==1.26.1
 celery[pytest]==5.2.7
+click_default_group==1.2.2
 cloud-sql-python-connector==1.9.2
 colorama>=0.4.3
 cryptography==42.0.0

src/fides/cli/__init__.py

@@ -23,6 +23,7 @@
 from .commands.db import database
 from .commands.deploy import deploy
 from .commands.generate import generate
+from .commands.pull import pull
 from .commands.scan import scan
 from .commands.ungrouped import (
     delete,
@@ -31,7 +32,6 @@
     init,
     list_resources,
     parse,
-    pull,
     push,
     status,
     webserver,

src/fides/cli/commands/pull.py

@@ -0,0 +1,178 @@
+from typing import Optional
+
+import rich_click as click
+from click_default_group import DefaultGroup
+
+from fides.cli.options import fides_key_argument, manifests_dir_argument
+from fides.cli.utils import with_analytics, with_server_health_check
+from fides.common.utils import echo_red
+from fides.core import parse as _parse
+from fides.core import pull as _pull
+from fides.core.utils import git_is_dirty
+
+
+@click.group(cls=DefaultGroup, default="all", default_if_no_args=True)  # type: ignore
+@click.pass_context
+def pull(ctx: click.Context) -> None:
+    """
+    Update local resource files based on the state of the objects on the server.
+    """
+
+
+@pull.command(name="all")  # type: ignore
+@click.pass_context
+@manifests_dir_argument
+@click.option(
+    "--all-resources",
+    "-a",
+    default=None,
+    help="Pulls all locally missing resources from the server into this file.",
+)
+@with_analytics
+@with_server_health_check
+def pull_all(
+    ctx: click.Context,
+    manifests_dir: str,
+    all_resources: Optional[str],
+) -> None:
+    """
+    Retrieve all resources from the server and update the local manifest files.
+    """
+
+    # Make the resources that are pulled configurable
+    config = ctx.obj["CONFIG"]
+    # Do this to validate the manifests since they won't get parsed during the pull process
+    _parse.parse(manifests_dir)
+    if git_is_dirty(manifests_dir):
+        echo_red(
+            f"There are unstaged changes in your manifest directory: '{manifests_dir}' \nAborting pull!"
+        )
+        raise SystemExit(1)
+    _pull.pull(
+        url=config.cli.server_url,
+        manifests_dir=manifests_dir,
+        headers=config.user.auth_header,
+        all_resources_file=all_resources,
+        fides_key=None,
+        resource_type=None,
+    )
+
+
+@pull.command(name="dataset")  # type: ignore
+@click.pass_context
+@fides_key_argument
+@manifests_dir_argument
+def dataset(
+    ctx: click.Context,
+    fides_key: str,
+    manifests_dir: str,
+) -> None:
+    """
+    Retrieve a specific dataset from the server and update the local manifest files.
+    """
+
+    config = ctx.obj["CONFIG"]
+    _pull.pull(
+        url=config.cli.server_url,
+        manifests_dir=manifests_dir,
+        headers=config.user.auth_header,
+        fides_key=fides_key,
+        resource_type="dataset",
+        all_resources_file=None,
+    )
+
+
+@pull.command(name="system")  # type: ignore
+@click.pass_context
+@fides_key_argument
+@manifests_dir_argument
+def system(
+    ctx: click.Context,
+    fides_key: str,
+    manifests_dir: str,
+) -> None:
+    """
+    Retrieve a specific system from the server and update the local manifest files.
+    """
+
+    config = ctx.obj["CONFIG"]
+    _pull.pull(
+        url=config.cli.server_url,
+        manifests_dir=manifests_dir,
+        headers=config.user.auth_header,
+        fides_key=fides_key,
+        resource_type="system",
+        all_resources_file=None,
+    )
+
+
+@pull.command(name="data_category")  # type: ignore
+@click.pass_context
+@fides_key_argument
+@manifests_dir_argument
+def data_category(
+    ctx: click.Context,
+    fides_key: str,
+    manifests_dir: str,
+) -> None:
+    """
+    Retrieve a specific data_category from the server and update the local manifest files.
+    """
+
+    config = ctx.obj["CONFIG"]
+    _pull.pull(
+        url=config.cli.server_url,
+        manifests_dir=manifests_dir,
+        headers=config.user.auth_header,
+        fides_key=fides_key,
+        resource_type="data_category",
+        all_resources_file=None,
+    )
+
+
+@pull.command(name="data_use")  # type: ignore
+@click.pass_context
+@fides_key_argument
+@manifests_dir_argument
+def data_use(
+    ctx: click.Context,
+    fides_key: str,
+    manifests_dir: str,
+) -> None:
+    """
+    Retrieve a specific data_use from the server and update the local manifest files.
+    """
+
+    config = ctx.obj["CONFIG"]
+    _pull.pull(
+        url=config.cli.server_url,
+        manifests_dir=manifests_dir,
+        headers=config.user.auth_header,
+        fides_key=fides_key,
+        resource_type="data_use",
+        all_resources_file=None,
+    )
+
+
+@pull.command(name="data_subject")  # type: ignore
+@click.pass_context
+@fides_key_argument
+@manifests_dir_argument
+def data_subject(
+    ctx: click.Context,
+    fides_key: str,
+    manifests_dir: str,
+) -> None:
+    """
+    Retrieve a specific data_subject from the server and update the local manifest files.
+    """
+
+    config = ctx.obj["CONFIG"]
+    _pull.pull(
+        url=config.cli.server_url,
+        manifests_dir=manifests_dir,
+        headers=config.user.auth_header,
+        fides_key=fides_key,
+        resource_type="data_subject",
+        all_resources_file=None,
+    )

src/fides/cli/commands/ungrouped.py

@@ -1,7 +1,6 @@
 """Contains all of the ungrouped CLI commands for fides."""
 
 from datetime import datetime, timezone
-from typing import Optional
 
 import rich_click as click
 import yaml
@@ -33,10 +32,8 @@
 from fides.core import audit as _audit
 from fides.core import evaluate as _evaluate
 from fides.core import parse as _parse
-from fides.core import pull as _pull
 from fides.core import push as _push
 from fides.core.api_helpers import get_server_resource, list_server_resources
-from fides.core.utils import git_is_dirty
 
 
 @click.command()  # type: ignore
@@ -311,36 +308,3 @@ def parse(ctx: click.Context, manifests_dir: str, verbose: bool = False) -> None
     taxonomy = _parse.parse(manifests_dir=manifests_dir)
     if verbose:
         pretty_echo(taxonomy.model_dump(mode="json"), color="green")
-
-
-@click.command()  # type: ignore
-@click.pass_context
-@manifests_dir_argument
-@click.option(
-    "--all-resources",
-    "-a",
-    default=None,
-    help="Pulls all locally missing resources from the server into this file.",
-)
-@with_analytics
-@with_server_health_check
-def pull(ctx: click.Context, manifests_dir: str, all_resources: Optional[str]) -> None:
-    """
-    Update local resource files based on the state of the objects on the server.
-    """
-
-    # Make the resources that are pulled configurable
-    config = ctx.obj["CONFIG"]
-    # Do this to validate the manifests since they won't get parsed during the pull process
-    _parse.parse(manifests_dir)
-    if git_is_dirty(manifests_dir):
-        echo_red(
-            f"There are unstaged changes in your manifest directory: '{manifests_dir}' \nAborting pull!"
-        )
-        raise SystemExit(1)
-    _pull.pull(
-        url=config.cli.server_url,
-        manifests_dir=manifests_dir,
-        headers=config.user.auth_header,
-        all_resources_file=all_resources,
-    )

src/fides/cli/options.py

@@ -13,6 +13,18 @@
 # If/when that issue is resolved, they can be removed.
 
 
+def diff_flag(command: Callable) -> Callable:
+    """Print any diffs between the local & server objects"""
+    command = click.option(
+        "--diff",
+        is_flag=True,
+        help="Print any diffs between the local & server objects",
+    )(
+        command
+    )  # type: ignore
+    return command
+
+
 def coverage_threshold_option(command: Callable) -> Callable:
     """An option decorator that sets a required coverage percentage."""
     command = click.option(
@@ -28,7 +40,7 @@ def coverage_threshold_option(command: Callable) -> Callable:
 
 
 def resource_type_argument(command: Callable) -> Callable:
-    "Add the resource_type option."
+    "Add the resource_type argument."
     command = click.argument(
         "resource_type",
         type=click.Choice(model_list, case_sensitive=False),
@@ -38,6 +50,18 @@ def resource_type_argument(command: Callable) -> Callable:
     return command
 
 
+def resource_type_option(command: Callable) -> Callable:
+    "Add the resource_type option."
+    command = click.option(
+        "--resource-type",
+        default="",
+        help=f"Choose from {str(model_list)}",
+    )(
+        command
+    )  # type: ignore
+    return command
+
+
 def fides_key_argument(command: Callable) -> Callable:
     "Add the fides_key argument."
     command = click.argument(