Add [tool] statistics

This commit is contained in:
niclas 2024-03-04 16:29:39 +01:00
parent 9a0fca647b
commit 94e0b855d1
5 changed files with 210 additions and 246 deletions

View file

@ -1,68 +1,26 @@
#!/usr/bin/python from modules.universe import Universe
from modules.site import IndexSite, StatisticsSite
from modules.galaxy import Galaxy import multiprocessing
from modules.statistics import Statistics from multiprocessing import Pool
import json import json
import os import os
import time import time
import sys
sys.setrecursionlimit(10000)
FILES_TO_IGNORE = []
CLUSTER_PATH = "../../clusters" CLUSTER_PATH = "../../clusters"
SITE_PATH = "./site/docs" SITE_PATH = "./site/docs"
GALAXY_PATH = "../../galaxies" GALAXY_PATH = "../../galaxies"
def get_cluster_relationships(cluster_data):
FILES_TO_IGNORE = [] # if you want to skip a specific cluster in the generation galaxy, cluster = cluster_data
relationships = universe.get_relationships_with_levels(universe.galaxies[galaxy].clusters[cluster])
print(f"Processed {galaxy}, {cluster}")
INTRO = """ return cluster, galaxy, relationships
# MISP Galaxy
The MISP galaxy offers a streamlined approach for representing large entities, known as clusters, which can be linked to MISP events or attributes. Each cluster consists of one or more elements, represented as key-value pairs. MISP galaxy comes with a default knowledge base, encompassing areas like Threat Actors, Tools, Ransomware, and ATT&CK matrices. However, users have the flexibility to modify, update, replace, or share these elements according to their needs.
Clusters and vocabularies within MISP galaxy can be utilized in their original form or as a foundational knowledge base. The distribution settings for each cluster can be adjusted, allowing for either restricted or wide dissemination.
Additionally, MISP galaxies enable the representation of existing standards like the MITRE ATT&CK framework, as well as custom matrices.
The aim is to provide a core set of clusters for organizations embarking on analysis, which can be further tailored to include localized, private information or additional, shareable data.
Clusters serve as an open and freely accessible knowledge base, which can be utilized and expanded within [MISP](https://www.misp-project.org/) or other threat intelligence platforms.
![Overview of the integration of MISP galaxy in the MISP Threat Intelligence Sharing Platform](https://raw.githubusercontent.com/MISP/misp-galaxy/aa41337fd78946a60aef3783f58f337d2342430a/doc/images/galaxy.png)
## Publicly available clusters
"""
STATISTICS = """
## Statistics
You can find some statistics about MISP galaxies [here](./statistics.md).
"""
CONTRIBUTING = """
# Contributing
In the dynamic realm of threat intelligence, a variety of models and approaches exist to systematically organize, categorize, and delineate threat actors, hazards, or activity groups. We embrace innovative methodologies for articulating threat intelligence. The galaxy model is particularly versatile, enabling you to leverage and integrate methodologies that you trust and are already utilizing within your organization or community.
We encourage collaboration and contributions to the [MISP Galaxy JSON files](https://github.com/MISP/misp-galaxy/). Feel free to fork the project, enhance existing elements or clusters, or introduce new ones. Your insights are valuable - share them with us through a pull-request.
"""
def write_galaxy_entry(galaxy, site_path, cluster_dict):
galaxy.write_entry(site_path, cluster_dict)
return f"Finished writing entry for {galaxy.name}"
def create_index(galaxies):
index_output = INTRO
for galaxy in galaxies:
index_output += f"- [{galaxy.name}](./{galaxy.json_file_name}/index.md)\n"
index_output += STATISTICS
index_output += CONTRIBUTING
return index_output
def get_deprecated_galaxy_files(): def get_deprecated_galaxy_files():
deprecated_galaxy_files = [] deprecated_galaxy_files = []
@ -74,9 +32,39 @@ def get_deprecated_galaxy_files():
return deprecated_galaxy_files return deprecated_galaxy_files
def cluster_transform_to_link(cluster):
placeholder = "__TMP__"
section = (
cluster
.value.lower()
.replace(" - ", placeholder) # Replace " - " first
.replace(" ", "-")
.replace("/", "")
.replace(":", "")
.replace(placeholder, "-")
)
galaxy_folder = cluster.galaxy.json_file_name.replace(".json", "")
return f"[{cluster.value} ({cluster.uuid})](../../{galaxy_folder}/index.md#{section})"
def main(): def galaxy_transform_to_link(galaxy):
galaxy_folder = galaxy.json_file_name.replace(".json", "")
return f"[{galaxy.galaxy_name}](../../{galaxy_folder}/index.md)"
def generate_relations_table(relationships):
markdown = "|Cluster A | Galaxy A | Cluster B | Galaxy B | Level { .graph } |\n"
markdown += "| --- | --- | --- | --- | --- |\n"
for from_cluster, to_cluster, level in relationships:
from_galaxy = from_cluster.galaxy
if to_cluster.value != "Private Cluster":
to_galaxy = to_cluster.galaxy
markdown += f"{cluster_transform_to_link(from_cluster)} | {galaxy_transform_to_link(from_galaxy)} | {cluster_transform_to_link(to_cluster)} | {galaxy_transform_to_link(to_galaxy)} | {level}\n"
else:
markdown += f"{cluster_transform_to_link(from_cluster)} | {galaxy_transform_to_link(from_galaxy)} | {to_cluster.value} | Unknown | {level}\n"
return markdown
if __name__ == "__main__":
start_time = time.time() start_time = time.time()
universe = Universe()
FILES_TO_IGNORE.extend(get_deprecated_galaxy_files()) FILES_TO_IGNORE.extend(get_deprecated_galaxy_files())
galaxies_fnames = [] galaxies_fnames = []
@ -85,45 +73,78 @@ def main():
galaxies_fnames.append(f) galaxies_fnames.append(f)
galaxies_fnames.sort() galaxies_fnames.sort()
galaxies = [] # Create the universe of clusters and galaxies
for galaxy in galaxies_fnames: for galaxy in galaxies_fnames:
with open(os.path.join(CLUSTER_PATH, galaxy)) as fr: with open(os.path.join(CLUSTER_PATH, galaxy)) as fr:
galaxy_json = json.load(fr) galaxy_json = json.load(fr)
galaxies.append( universe.add_galaxy(galaxy_name=galaxy_json["name"], json_file_name=galaxy, authors=galaxy_json["authors"], description=galaxy_json["description"])
Galaxy( for cluster in galaxy_json["values"]:
cluster_list=galaxy_json["values"], universe.add_cluster(
authors=galaxy_json["authors"], galaxy_name=galaxy_json.get("name", None),
description=galaxy_json["description"], uuid=cluster.get("uuid", None),
name=galaxy_json["name"], description=cluster.get("description", None),
json_file_name=galaxy.split(".")[0], value=cluster.get("value", None),
) meta=cluster.get("meta", None)
) )
cluster_dict = {}
for galaxy in galaxies:
for cluster in galaxy.clusters:
cluster_dict[cluster.uuid] = cluster
statistics = Statistics(cluster_dict=cluster_dict) # Define the relationships between clusters
for galaxy in galaxies: for galaxy in galaxies_fnames:
for cluster in galaxy.clusters: with open(os.path.join(CLUSTER_PATH, galaxy)) as fr:
statistics.add_cluster(cluster) galaxy_json = json.load(fr)
for cluster in galaxy_json["values"]:
if "related" in cluster:
for related in cluster["related"]:
universe.define_relationship(cluster["uuid"], related["dest-uuid"])
# Write files tasks = []
for galaxy_name, galaxy in universe.galaxies.items():
for cluster_name, cluster in galaxy.clusters.items():
tasks.append((galaxy_name, cluster_name))
with Pool(processes=multiprocessing.cpu_count()) as pool:
result = pool.map(get_cluster_relationships, tasks)
for cluster, galaxy, relationships in result:
universe.galaxies[galaxy].clusters[cluster].relationships = relationships
print("All clusters processed.")
print(f"Finished relations in {time.time() - start_time} seconds")
# Write output
if not os.path.exists(SITE_PATH): if not os.path.exists(SITE_PATH):
os.mkdir(SITE_PATH) os.mkdir(SITE_PATH)
index = IndexSite(SITE_PATH)
index.add_content("# MISP Galaxy\n\nThe MISP galaxy offers a streamlined approach for representing large entities, known as clusters, which can be linked to MISP events or attributes. Each cluster consists of one or more elements, represented as key-value pairs. MISP galaxy comes with a default knowledge base, encompassing areas like Threat Actors, Tools, Ransomware, and ATT&CK matrices. However, users have the flexibility to modify, update, replace, or share these elements according to their needs.\n\nClusters and vocabularies within MISP galaxy can be utilized in their original form or as a foundational knowledge base. The distribution settings for each cluster can be adjusted, allowing for either restricted or wide dissemination.\n\nAdditionally, MISP galaxies enable the representation of existing standards like the MITRE ATT&CK™ framework, as well as custom matrices.\n\nThe aim is to provide a core set of clusters for organizations embarking on analysis, which can be further tailored to include localized, private information or additional, shareable data.\n\nClusters serve as an open and freely accessible knowledge base, which can be utilized and expanded within [MISP](https://www.misp-project.org/) or other threat intelligence platforms.\n\n![Overview of the integration of MISP galaxy in the MISP Threat Intelligence Sharing Platform](https://raw.githubusercontent.com/MISP/misp-galaxy/aa41337fd78946a60aef3783f58f337d2342430a/doc/images/galaxy.png)\n\n## Publicly available clusters\n")
index.add_toc(universe.galaxies.values())
index.add_content("## Statistics\n\nYou can find some statistics about MISP galaxies [here](./statistics.md).\n\n")
index.add_content("# Contributing\n\nIn the dynamic realm of threat intelligence, a variety of models and approaches exist to systematically organize, categorize, and delineate threat actors, hazards, or activity groups. We embrace innovative methodologies for articulating threat intelligence. The galaxy model is particularly versatile, enabling you to leverage and integrate methodologies that you trust and are already utilizing within your organization or community.\n\nWe encourage collaboration and contributions to the [MISP Galaxy JSON files](https://github.com/MISP/misp-galaxy/). Feel free to fork the project, enhance existing elements or clusters, or introduce new ones. Your insights are valuable - share them with us through a pull-request.\n")
index.write_entry()
for galaxy in galaxies: statistics = StatisticsSite(SITE_PATH)
galaxy.write_entry(SITE_PATH, cluster_dict) statistics.add_galaxy_statistics(universe.galaxies.values())
statistics.add_cluster_statistics([cluster for galaxy in universe.galaxies.values() for cluster in galaxy.clusters.values()])
statistics.add_relation_statistics([cluster for galaxy in universe.galaxies.values() for cluster in galaxy.clusters.values()])
statistics.write_entry()
index_output = create_index(galaxies) for galaxy in universe.galaxies.values():
galaxy.write_entry(SITE_PATH)
statistics.write_entry(SITE_PATH) for galaxy in universe.galaxies.values():
galaxy_path = os.path.join(SITE_PATH, f"{galaxy.json_file_name}".replace(".json", ""))
if not os.path.exists(galaxy_path):
os.mkdir(galaxy_path)
relation_path = os.path.join(galaxy_path, "relations")
if not os.path.exists(relation_path):
os.mkdir(relation_path)
with open(os.path.join(relation_path, ".pages"), "w") as index:
index.write(f"hide: true\n")
with open(os.path.join(SITE_PATH, "index.md"), "w") as index: for cluster in galaxy.clusters.values():
index.write(index_output) if cluster.relationships:
print(f"Writing {cluster.uuid}.md")
with open(os.path.join(relation_path, f"{cluster.uuid}.md"), "w") as index:
index.write(generate_relations_table(cluster.relationships))
print(f"Finished file creation in {time.time() - start_time} seconds") print(f"Finished in {time.time() - start_time} seconds")
if __name__ == "__main__":
main()

View file

@ -1,150 +0,0 @@
from modules.universe import Universe
import multiprocessing
from multiprocessing import Pool
import json
import os
import time
import sys
sys.setrecursionlimit(10000)
FILES_TO_IGNORE = []
CLUSTER_PATH = "../../clusters"
SITE_PATH = "./site/docs"
GALAXY_PATH = "../../galaxies"
def get_cluster_relationships(cluster_data):
# Unpack cluster data
galaxy, cluster = cluster_data
relationships = universe.get_relationships_with_levels(universe.galaxies[galaxy].clusters[cluster])
print(f"Processed {galaxy}, {cluster}")
return cluster, galaxy, relationships
def get_deprecated_galaxy_files():
deprecated_galaxy_files = []
for f in os.listdir(GALAXY_PATH):
with open(os.path.join(GALAXY_PATH, f)) as fr:
galaxy_json = json.load(fr)
if "namespace" in galaxy_json and galaxy_json["namespace"] == "deprecated":
deprecated_galaxy_files.append(f)
return deprecated_galaxy_files
def cluster_transform_to_link(cluster):
placeholder = "__TMP__"
section = (
cluster
.value.lower()
.replace(" - ", placeholder) # Replace " - " first
.replace(" ", "-")
.replace("/", "")
.replace(":", "")
.replace(placeholder, "-")
)
galaxy_folder = cluster.galaxy.json_file_name.replace(".json", "")
return f"[{cluster.value} ({cluster.uuid})](../../{galaxy_folder}/index.md#{section})"
def galaxy_transform_to_link(galaxy):
galaxy_folder = galaxy.json_file_name.replace(".json", "")
return f"[{galaxy.galaxy_name}](../../{galaxy_folder}/index.md)"
def generate_relations_table(relationships):
markdown = "|Cluster A | Galaxy A | Cluster B | Galaxy B | Level { .graph } |\n"
markdown += "| --- | --- | --- | --- | --- |\n"
for from_cluster, to_cluster, level in relationships:
from_galaxy = from_cluster.galaxy
if to_cluster.value != "Private Cluster":
to_galaxy = to_cluster.galaxy
markdown += f"{cluster_transform_to_link(from_cluster)} | {galaxy_transform_to_link(from_galaxy)} | {cluster_transform_to_link(to_cluster)} | {galaxy_transform_to_link(to_galaxy)} | {level}\n"
else:
markdown += f"{cluster_transform_to_link(from_cluster)} | {galaxy_transform_to_link(from_galaxy)} | {to_cluster.value} | Unknown | {level}\n"
return markdown
def generate_index_page(galaxies):
index_output = "# MISP Galaxy\n\nThe MISP galaxy offers a streamlined approach for representing large entities, known as clusters, which can be linked to MISP events or attributes. Each cluster consists of one or more elements, represented as key-value pairs. MISP galaxy comes with a default knowledge base, encompassing areas like Threat Actors, Tools, Ransomware, and ATT&CK matrices. However, users have the flexibility to modify, update, replace, or share these elements according to their needs.\n\nClusters and vocabularies within MISP galaxy can be utilized in their original form or as a foundational knowledge base. The distribution settings for each cluster can be adjusted, allowing for either restricted or wide dissemination.\n\nAdditionally, MISP galaxies enable the representation of existing standards like the MITRE ATT&CK™ framework, as well as custom matrices.\n\nThe aim is to provide a core set of clusters for organizations embarking on analysis, which can be further tailored to include localized, private information or additional, shareable data.\n\nClusters serve as an open and freely accessible knowledge base, which can be utilized and expanded within [MISP](https://www.misp-project.org/) or other threat intelligence platforms.\n\n![Overview of the integration of MISP galaxy in the MISP Threat Intelligence Sharing Platform](https://raw.githubusercontent.com/MISP/misp-galaxy/aa41337fd78946a60aef3783f58f337d2342430a/doc/images/galaxy.png)\n\n## Publicly available clusters\n"
for galaxy in galaxies:
galaxy_folder = galaxy.json_file_name.replace(".json", "")
index_output += f"- [{galaxy.galaxy_name}](./{galaxy_folder}/index.md)\n"
index_output += "## Statistics\n\nYou can find some statistics about MISP galaxies [here](./statistics.md).\n"
index_output += "# Contributing\n\nIn the dynamic realm of threat intelligence, a variety of models and approaches exist to systematically organize, categorize, and delineate threat actors, hazards, or activity groups. We embrace innovative methodologies for articulating threat intelligence. The galaxy model is particularly versatile, enabling you to leverage and integrate methodologies that you trust and are already utilizing within your organization or community.\n\nWe encourage collaboration and contributions to the [MISP Galaxy JSON files](https://github.com/MISP/misp-galaxy/). Feel free to fork the project, enhance existing elements or clusters, or introduce new ones. Your insights are valuable - share them with us through a pull-request.\n"
return index_output
if __name__ == "__main__":
start_time = time.time()
universe = Universe()
FILES_TO_IGNORE.extend(get_deprecated_galaxy_files())
galaxies_fnames = []
for f in os.listdir(CLUSTER_PATH):
if ".json" in f and f not in FILES_TO_IGNORE:
galaxies_fnames.append(f)
galaxies_fnames.sort()
# Create the universe of clusters and galaxies
for galaxy in galaxies_fnames:
with open(os.path.join(CLUSTER_PATH, galaxy)) as fr:
galaxy_json = json.load(fr)
universe.add_galaxy(galaxy_name=galaxy_json["name"], json_file_name=galaxy, authors=galaxy_json["authors"], description=galaxy_json["description"])
for cluster in galaxy_json["values"]:
universe.add_cluster(
galaxy_name=galaxy_json.get("name", None),
uuid=cluster.get("uuid", None),
description=cluster.get("description", None),
value=cluster.get("value", None),
meta=cluster.get("meta", None)
)
# Define the relationships between clusters
for galaxy in galaxies_fnames:
with open(os.path.join(CLUSTER_PATH, galaxy)) as fr:
galaxy_json = json.load(fr)
for cluster in galaxy_json["values"]:
if "related" in cluster:
for related in cluster["related"]:
universe.define_relationship(cluster["uuid"], related["dest-uuid"])
tasks = []
for galaxy_name, galaxy in universe.galaxies.items():
for cluster_name, cluster in galaxy.clusters.items():
tasks.append((galaxy_name, cluster_name))
with Pool(processes=multiprocessing.cpu_count()) as pool:
result = pool.map(get_cluster_relationships, tasks)
for cluster, galaxy, relationships in result:
universe.galaxies[galaxy].clusters[cluster].relationships = relationships
print("All clusters processed.")
print(f"Finished relations in {time.time() - start_time} seconds")
# Write output
if not os.path.exists(SITE_PATH):
os.mkdir(SITE_PATH)
with open(os.path.join(SITE_PATH, "index.md"), "w") as index:
index.write(generate_index_page(universe.galaxies.values()))
for galaxy in universe.galaxies.values():
galaxy.write_entry(SITE_PATH)
for galaxy in universe.galaxies.values():
galaxy_path = os.path.join(SITE_PATH, f"{galaxy.json_file_name}".replace(".json", ""))
if not os.path.exists(galaxy_path):
os.mkdir(galaxy_path)
relation_path = os.path.join(galaxy_path, "relations")
if not os.path.exists(relation_path):
os.mkdir(relation_path)
with open(os.path.join(relation_path, ".pages"), "w") as index:
index.write(f"hide: true\n")
for cluster in galaxy.clusters.values():
if cluster.relationships:
print(f"Writing {cluster.uuid}.md")
with open(os.path.join(relation_path, f"{cluster.uuid}.md"), "w") as index:
index.write(generate_relations_table(cluster.relationships))
print(f"Finished in {time.time() - start_time} seconds")

View file

@ -0,0 +1,81 @@
import os
from utils.helper import create_bar_chart, get_top_x, create_pie_chart
class Site:
def __init__(self, path, name) -> None:
self.path = path
self.name = name
self.content = ""
def add_content(self, content):
self.content += content
def write_entry(self):
with open(os.path.join(self.path, self.name), "w") as index:
index.write(self.content)
class IndexSite(Site):
def __init__(self, path) -> None:
super().__init__(path=path, name="index.md")
def add_toc(self, galaxies):
for galaxy in galaxies:
galaxy_folder = galaxy.json_file_name.replace(".json", "")
self.add_content(f"- [{galaxy.galaxy_name}](./{galaxy_folder}/index.md)\n")
self.add_content("\n")
class StatisticsSite(Site):
def __init__(self, path) -> None:
super().__init__(path=path, name="statistics.md")
def add_galaxy_statistics(self, galaxies):
galaxy_cluster_count = {galaxy.galaxy_name: len(galaxy.clusters) for galaxy in galaxies}
top_20 = get_top_x(galaxy_cluster_count, 20)
flop_20 = get_top_x(galaxy_cluster_count, 20, False)
self.add_content(f"# Galaxy statistics\n")
self.add_content(f"## Galaxies with the most clusters\n")
self.add_content(create_bar_chart(x_axis="Galaxy", y_axis="Count", values=top_20))
self.add_content(f"## Galaxies with the least clusters\n")
self.add_content(create_bar_chart(x_axis="Galaxy", y_axis="Count", values=flop_20))
def add_cluster_statistics(self, clusters):
public_clusters = 0
private_clusters = 0
for cluster in clusters:
if cluster.value == "Private Cluster":
private_clusters += 1
else:
public_clusters += 1
values = {"Public clusters": public_clusters, "Private clusters": private_clusters}
self.add_content(f"# Cluster statistics\n")
self.add_content(f"## Number of clusters\n")
self.add_content(f"Here you can find the total number of clusters including public and private clusters.The number of public clusters has been calculated based on the number of unique Clusters in the MISP galaxy JSON files. The number of private clusters could only be approximated based on the number of relations to non-existing clusters. Therefore the number of private clusters is not accurate and only an approximation.\n\n")
self.add_content(create_pie_chart(sector="Type", unit="Count", values=values))
def add_relation_statistics(self, clusters):
cluster_relations = {}
private_relations = 0
public_relations = 0
for cluster in clusters:
cluster_relations[cluster.uuid] = len(cluster.relations)
for relation in cluster.relations:
if relation.to_cluster.value == "Private Cluster":
private_relations += 1
else:
public_relations += 1
top_20 = get_top_x(cluster_relations, 20)
flop_20 = get_top_x(cluster_relations, 20, False)
self.add_content(f"# Relation statistics\n")
self.add_content(f"Here you can find the total number of relations including public and private relations. The number includes relations between public clusters and relations between public and private clusters. Therefore relatons between private clusters are not included in the statistics.\n\n")
self.add_content(f"## Number of relations\n")
self.add_content(create_pie_chart(sector="Type", unit="Count", values={"Public relations": public_relations, "Private relations": private_relations}))
self.add_content(f"**Average number of relations per cluster**: {int(sum(cluster_relations.values()) / len(cluster_relations))}\n")
self.add_content(f"## Cluster with the most relations\n")
self.add_content(create_bar_chart(x_axis="Cluster", y_axis="Count", values=top_20))
self.add_content(f"## Cluster with the least relations\n")
self.add_content(create_bar_chart(x_axis="Cluster", y_axis="Count", values=flop_20))
def add_synonym_statistics(self, clusters):
pass

View file

@ -21,13 +21,16 @@ class Universe:
cluster_a = None cluster_a = None
cluster_b = None cluster_b = None
if cluster_a_id == cluster_b_id:
return
# Search for Cluster A and Cluster B in all galaxies # Search for Cluster A and Cluster B in all galaxies
for galaxy in self.galaxies.values(): for galaxy in self.galaxies.values():
if cluster_a_id in galaxy.clusters: if cluster_a_id in galaxy.clusters:
cluster_a = galaxy.clusters[cluster_a_id] cluster_a = galaxy.clusters[cluster_a_id]
if cluster_b_id in galaxy.clusters: if cluster_b_id in galaxy.clusters:
cluster_b = galaxy.clusters[cluster_b_id] cluster_b = galaxy.clusters[cluster_b_id]
if cluster_a and cluster_b: # Both clusters found if cluster_a and cluster_b:
break break
# If both clusters are found, define the relationship # If both clusters are found, define the relationship
@ -35,7 +38,6 @@ class Universe:
cluster_a.add_outbound_relationship(cluster_b) cluster_a.add_outbound_relationship(cluster_b)
cluster_b.add_inbound_relationship(cluster_a) cluster_b.add_inbound_relationship(cluster_a)
else: else:
# If Cluster B is not found, create a private cluster relationship for Cluster A
if cluster_a: if cluster_a:
private_cluster = Cluster(uuid=cluster_b_id, galaxy=None, description=None, value="Private Cluster", meta=None) private_cluster = Cluster(uuid=cluster_b_id, galaxy=None, description=None, value="Private Cluster", meta=None)
cluster_a.add_outbound_relationship(private_cluster) cluster_a.add_outbound_relationship(private_cluster)
@ -67,26 +69,18 @@ class Universe:
if neighbor not in visited and neighbor.value != "Private Cluster": if neighbor not in visited and neighbor.value != "Private Cluster":
queue.append((neighbor, level + 1)) queue.append((neighbor, level + 1))
# count = 0
# Convert the defaultdict to a list of tuples, ignoring direction # Convert the defaultdict to a list of tuples, ignoring direction
processed_relationships = [] processed_relationships = []
for link, lvl in relationships.items(): for link, lvl in relationships.items():
# Extract clusters from the frozenset; direction is irrelevant # Extract clusters from the frozenset; direction is irrelevant
clusters = list(link) clusters = list(link)
if len(clusters) != 2:
# count += 1
continue
# Arbitrarily choose the first cluster as 'source' for consistency # Arbitrarily choose the first cluster as 'source' for consistency
if clusters[0].value == "Private Cluster": if clusters[0].value == "Private Cluster":
processed_relationships.append((clusters[1], clusters[0], lvl)) processed_relationships.append((clusters[1], clusters[0], lvl))
else: else:
processed_relationships.append((clusters[0], clusters[1], lvl)) processed_relationships.append((clusters[0], clusters[1], lvl))
# except:
# processed_relationships.append((clusters[0], clusters[0], lvl)) # This is wrong just for testing!!!
# print(f"Count: {count}")
return processed_relationships return processed_relationships
return bfs_with_undirected_relationships(start_cluster) return bfs_with_undirected_relationships(start_cluster)

View file

@ -18,4 +18,22 @@ def name_to_section(name):
.replace("/", "") .replace("/", "")
.replace(":", "") .replace(":", "")
.replace(placeholder, "-") .replace(placeholder, "-")
) # Replace the placeholder with "-" ) # Replace the placeholder with "-"
def create_bar_chart(x_axis, y_axis, values, log=False):
if not log:
chart = f"| No. | {x_axis} | {y_axis} {{ .bar-chart }}|\n"
else:
chart = f"| No. | {x_axis} | {y_axis} {{ .log-bar-chart }}|\n"
chart += f"|----|--------|-------|\n"
for i, x, y in enumerate(values):
chart += f"| {i+1} | {x} | {y} |\n"
return chart
def create_pie_chart(sector, unit, values):
chart = f"| No. | {sector} | {unit} {{ .pie-chart }}|\n"
chart += f"|----|--------|-------|\n"
for i, x, y in enumerate(values):
chart += f"| {i+1} | {x} | {y} |\n"
return chart