pulling blocks from catalog

[WillRaphaelson]

Uncheckedin script used to cull the blocks metadata file, removing the archived collections

import json
import httpx

import httpx

def list_files_in_repo(owner, repo, path=""):
    """
    Lists files in a given GitHub repository at the specified path.

    Args:
    owner (str): GitHub username or organization
    repo (str): Repository name
    path (str): Directory path within the repository

    Returns:
    list of dict: List of files and directories in the specified path
    """
    api_url = f"https://api.github.com/repos/{owner}/{repo}/contents/{path}"
    response = httpx.get(api_url)

    # Check if the request was successful
    if response.status_code == 200:
        return response.json()
    else:
        print(f"Failed to retrieve data: {response.status_code}")
        return []

# Example usage
owner = "PrefectHQ"  # Replace with the actual owner's name
repo = "Prefect"  # Replace with the actual repository name
path = "docs/integrations/catalog"  # Specify path or leave empty for root directory
files = list_files_in_repo(owner, repo, path)




list_of_valid_collections = [file['name'][:-5] for file in files if file['type'] == 'file' and file['name'] != "TEMPLATE.yaml"]

list_of_valid_collections.append("prefect")

with open("views/aggregate-block-metadata.json", 'r') as file:
    data = json.load(file)

print(len(data))

new_dict = {key: value for key, value in data.items() if key in list_of_valid_collections}
new_dict = dict(sorted(new_dict.items()))

# print(len(new_dict))

print(len(new_dict["prefect"]["block_types"]))

prefect_dict = {key: value for key, value in new_dict["prefect"]["block_types"].items() if key not in ("string", "date-time", "json")}

new_dict["prefect"]["block_types"] = prefect_dict

json.dump(new_dict, open("views/aggregate-block-metadata.json", 'w'), indent=2)

[zzstoatzz]

lgtm!

[zzstoatzz]

we're removing primitives here?