mirror of
https://github.com/MISP/misp-galaxy.git
synced 2024-11-26 16:57:18 +00:00
GitHub
commit
0c58c95f6d
2 changed files with 276 additions and 168 deletions
|
|
@ -8,10 +8,10 @@ from typing import List
|
|||
|
||||
import validators
|
||||
|
||||
CLUSTER_PATH = '../../clusters'
|
||||
SITE_PATH = './site/docs'
|
||||
CLUSTER_PATH = "../../clusters"
|
||||
SITE_PATH = "./site/docs"
|
||||
|
||||
FILES_TO_IGNORE = [] # if you want to skip a specific cluster in the generation
|
||||
FILES_TO_IGNORE = [] # if you want to skip a specific cluster in the generation
|
||||
|
||||
# Variables for statistics
|
||||
public_relations_count = 0
|
||||
|
|
@ -41,7 +41,7 @@ Clusters serve as an open and freely accessible knowledge base, which can be uti
|
|||
|
||||
"""
|
||||
|
||||
STATISTICS= """
|
||||
STATISTICS = """
|
||||
## Statistics
|
||||
|
||||
You can find some statistics about MISP galaxies [here](./statistics.md).
|
||||
|
|
@ -58,8 +58,11 @@ We encourage collaboration and contributions to the [MISP Galaxy JSON files](htt
|
|||
|
||||
"""
|
||||
|
||||
class Galaxy():
|
||||
def __init__(self, cluster_list: List[dict], authors, description, name, json_file_name):
|
||||
|
||||
class Galaxy:
|
||||
def __init__(
|
||||
self, cluster_list: List[dict], authors, description, name, json_file_name
|
||||
):
|
||||
self.cluster_list = cluster_list
|
||||
self.authors = authors
|
||||
self.description = description
|
||||
|
|
@ -70,39 +73,41 @@ class Galaxy():
|
|||
|
||||
def _create_metadata_entry(self):
|
||||
self.entry += "---\n"
|
||||
self.entry += f'title: {self.name}\n'
|
||||
meta_description = self.description.replace("\"", "-")
|
||||
self.entry += f'description: {meta_description}\n'
|
||||
self.entry += f"title: {self.name}\n"
|
||||
meta_description = self.description.replace('"', "-")
|
||||
self.entry += f"description: {meta_description}\n"
|
||||
self.entry += "---\n"
|
||||
|
||||
def _create_title_entry(self):
|
||||
self.entry += f'# {self.name}\n'
|
||||
self.entry += f"# {self.name}\n"
|
||||
|
||||
def _create_description_entry(self):
|
||||
self.entry += f'{self.description}\n'
|
||||
self.entry += f"{self.description}\n"
|
||||
|
||||
def _create_authors_entry(self):
|
||||
if self.authors:
|
||||
self.entry += f'\n'
|
||||
self.entry += f"\n"
|
||||
self.entry += f'??? info "Authors"\n'
|
||||
self.entry += f'\n'
|
||||
self.entry += f' | Authors and/or Contributors|\n'
|
||||
self.entry += f' |----------------------------|\n'
|
||||
self.entry += f"\n"
|
||||
self.entry += f" | Authors and/or Contributors|\n"
|
||||
self.entry += f" |----------------------------|\n"
|
||||
for author in self.authors:
|
||||
self.entry += f' |{author}|\n'
|
||||
self.entry += f" |{author}|\n"
|
||||
|
||||
def _create_clusters(self):
|
||||
clusters = []
|
||||
for cluster in self.cluster_list:
|
||||
clusters.append(Cluster(
|
||||
value=cluster.get('value', None),
|
||||
description=cluster.get('description', None),
|
||||
uuid=cluster.get('uuid', None),
|
||||
date=cluster.get('date', None),
|
||||
related_list=cluster.get('related', None),
|
||||
meta=cluster.get('meta', None),
|
||||
galaxie=self
|
||||
))
|
||||
clusters.append(
|
||||
Cluster(
|
||||
value=cluster.get("value", None),
|
||||
description=cluster.get("description", None),
|
||||
uuid=cluster.get("uuid", None),
|
||||
date=cluster.get("date", None),
|
||||
related_list=cluster.get("related", None),
|
||||
meta=cluster.get("meta", None),
|
||||
galaxie=self,
|
||||
)
|
||||
)
|
||||
return clusters
|
||||
|
||||
def _create_clusters_entry(self, cluster_dict):
|
||||
|
|
@ -122,10 +127,11 @@ class Galaxy():
|
|||
galaxy_path = os.path.join(path, self.json_file_name)
|
||||
if not os.path.exists(galaxy_path):
|
||||
os.mkdir(galaxy_path)
|
||||
with open(os.path.join(galaxy_path, 'index.md'), "w") as index:
|
||||
with open(os.path.join(galaxy_path, "index.md"), "w") as index:
|
||||
index.write(self.entry)
|
||||
|
||||
class Cluster():
|
||||
|
||||
class Cluster:
|
||||
def __init__(self, description, uuid, date, value, related_list, meta, galaxie):
|
||||
self.description = description
|
||||
self.uuid = uuid
|
||||
|
|
@ -141,61 +147,61 @@ class Cluster():
|
|||
public_clusters_dict[self.uuid] = self.galaxie
|
||||
|
||||
def _create_title_entry(self):
|
||||
self.entry += f'## {self.value}\n'
|
||||
self.entry += f'\n'
|
||||
self.entry += f"## {self.value}\n"
|
||||
self.entry += f"\n"
|
||||
|
||||
def _create_description_entry(self):
|
||||
if self.description:
|
||||
self.entry += f'{self.description}\n'
|
||||
self.entry += f"{self.description}\n"
|
||||
|
||||
def _create_synonyms_entry(self):
|
||||
if isinstance(self.meta, dict) and self.meta.get('synonyms'):
|
||||
self.entry += f'\n'
|
||||
if isinstance(self.meta, dict) and self.meta.get("synonyms"):
|
||||
self.entry += f"\n"
|
||||
self.entry += f'??? info "Synonyms"\n'
|
||||
self.entry += f'\n'
|
||||
self.entry += f"\n"
|
||||
self.entry += f' "synonyms" in the meta part typically refer to alternate names or labels that are associated with a particular {self.value}.\n\n'
|
||||
self.entry += f' | Known Synonyms |\n'
|
||||
self.entry += f' |---------------------|\n'
|
||||
self.entry += f" | Known Synonyms |\n"
|
||||
self.entry += f" |---------------------|\n"
|
||||
global synonyms_count_dict
|
||||
synonyms_count = 0
|
||||
for synonym in sorted(self.meta['synonyms']):
|
||||
for synonym in sorted(self.meta["synonyms"]):
|
||||
synonyms_count += 1
|
||||
self.entry += f' | `{synonym}` |\n'
|
||||
self.entry += f" | `{synonym}` |\n"
|
||||
synonyms_count_dict[self.uuid] = synonyms_count
|
||||
|
||||
def _create_uuid_entry(self):
|
||||
if self.uuid:
|
||||
self.entry += f'\n'
|
||||
self.entry += f"\n"
|
||||
self.entry += f'??? tip "Internal MISP references"\n'
|
||||
self.entry += f'\n'
|
||||
self.entry += f' UUID `{self.uuid}` which can be used as unique global reference for `{self.value}` in MISP communities and other software using the MISP galaxy\n'
|
||||
self.entry += f'\n'
|
||||
self.entry += f"\n"
|
||||
self.entry += f" UUID `{self.uuid}` which can be used as unique global reference for `{self.value}` in MISP communities and other software using the MISP galaxy\n"
|
||||
self.entry += f"\n"
|
||||
|
||||
def _create_refs_entry(self):
|
||||
if isinstance(self.meta, dict) and self.meta.get('refs'):
|
||||
self.entry += f'\n'
|
||||
if isinstance(self.meta, dict) and self.meta.get("refs"):
|
||||
self.entry += f"\n"
|
||||
self.entry += f'??? info "External references"\n'
|
||||
self.entry += f'\n'
|
||||
self.entry += f"\n"
|
||||
|
||||
for ref in self.meta['refs']:
|
||||
for ref in self.meta["refs"]:
|
||||
if validators.url(ref):
|
||||
self.entry += f' - [{ref}]({ref}) - :material-archive: :material-arrow-right: [webarchive](https://web.archive.org/web/*/{ref})\n'
|
||||
self.entry += f" - [{ref}]({ref}) - :material-archive: :material-arrow-right: [webarchive](https://web.archive.org/web/*/{ref})\n"
|
||||
else:
|
||||
self.entry += f' - {ref}\n'
|
||||
self.entry += f" - {ref}\n"
|
||||
|
||||
self.entry += f'\n'
|
||||
self.entry += f"\n"
|
||||
|
||||
def _create_associated_metadata_entry(self):
|
||||
if isinstance(self.meta, dict):
|
||||
excluded_meta = ['synonyms', 'refs']
|
||||
self.entry += f'\n'
|
||||
excluded_meta = ["synonyms", "refs"]
|
||||
self.entry += f"\n"
|
||||
self.entry += f'??? info "Associated metadata"\n'
|
||||
self.entry += f'\n'
|
||||
self.entry += f' |Metadata key {{ .no-filter }} |Value|\n'
|
||||
self.entry += f' |-----------------------------------|-----|\n'
|
||||
self.entry += f"\n"
|
||||
self.entry += f" |Metadata key {{ .no-filter }} |Value|\n"
|
||||
self.entry += f" |-----------------------------------|-----|\n"
|
||||
for meta in sorted(self.meta.keys()):
|
||||
if meta not in excluded_meta:
|
||||
self.entry += f' | {meta} | {self.meta[meta]} |\n'
|
||||
self.entry += f" | {meta} | {self.meta[meta]} |\n"
|
||||
|
||||
def get_related_clusters(self, cluster_dict, depth=-1, visited=None, level=1):
|
||||
global public_relations_count
|
||||
|
|
@ -228,7 +234,21 @@ class Cluster():
|
|||
private_relations_count += 1
|
||||
if dest_uuid not in private_clusters:
|
||||
private_clusters.append(dest_uuid)
|
||||
related_clusters.append((self, Cluster(value="Private Cluster", uuid=dest_uuid, date=None, description=None, related_list=None, meta=None, galaxie=None), level))
|
||||
related_clusters.append(
|
||||
(
|
||||
self,
|
||||
Cluster(
|
||||
value="Private Cluster",
|
||||
uuid=dest_uuid,
|
||||
date=None,
|
||||
description=None,
|
||||
related_list=None,
|
||||
meta=None,
|
||||
galaxie=None,
|
||||
),
|
||||
level,
|
||||
)
|
||||
)
|
||||
continue
|
||||
|
||||
related_cluster = cluster_dict[dest_uuid]
|
||||
|
|
@ -237,10 +257,15 @@ class Cluster():
|
|||
|
||||
related_clusters.append((self, related_cluster, level))
|
||||
|
||||
if (depth > 1 or depth == -1) and (cluster["dest-uuid"] not in visited or visited[cluster["dest-uuid"]] > level + 1):
|
||||
if (depth > 1 or depth == -1) and (
|
||||
cluster["dest-uuid"] not in visited
|
||||
or visited[cluster["dest-uuid"]] > level + 1
|
||||
):
|
||||
new_depth = depth - 1 if depth > 1 else -1
|
||||
if cluster["dest-uuid"] in cluster_dict:
|
||||
related_clusters += cluster_dict[cluster["dest-uuid"]].get_related_clusters(cluster_dict, new_depth, visited, level+1)
|
||||
related_clusters += cluster_dict[
|
||||
cluster["dest-uuid"]
|
||||
].get_related_clusters(cluster_dict, new_depth, visited, level + 1)
|
||||
|
||||
if empty_uuids > 0:
|
||||
empty_uuids_dict[self.value] = empty_uuids
|
||||
|
|
@ -268,43 +293,51 @@ class Cluster():
|
|||
|
||||
else:
|
||||
cluster_dict[key1] = cluster
|
||||
related_clusters = [cluster for cluster in related_clusters if cluster not in to_remove]
|
||||
related_clusters = [
|
||||
cluster for cluster in related_clusters if cluster not in to_remove
|
||||
]
|
||||
|
||||
return related_clusters
|
||||
|
||||
def _create_related_entry(self):
|
||||
self.entry += f'\n'
|
||||
self.entry += f"\n"
|
||||
self.entry += f'??? info "Related clusters"\n'
|
||||
self.entry += f'\n'
|
||||
self.entry += f' To see the related clusters, click [here](./relations/{self.uuid}.md).\n'
|
||||
self.entry += f"\n"
|
||||
self.entry += f" To see the related clusters, click [here](./relations/{self.uuid}.md).\n"
|
||||
|
||||
def _get_related_entry(self, relations):
|
||||
output = ""
|
||||
output += f'## Related clusters for {self.value}\n'
|
||||
output += f'\n'
|
||||
output += f'| Cluster A | Cluster B | Level {{ .graph }} |\n'
|
||||
output += f'|-----------|-----------|-------|\n'
|
||||
output += f"## Related clusters for {self.value}\n"
|
||||
output += f"\n"
|
||||
output += f"| Cluster A | Cluster B | Level {{ .graph }} |\n"
|
||||
output += f"|-----------|-----------|-------|\n"
|
||||
for relation in relations:
|
||||
placeholder = "__TMP__"
|
||||
|
||||
cluster_a_section = (relation[0].value.lower()
|
||||
.replace(" - ", placeholder) # Replace " - " first
|
||||
.replace(" ", "-")
|
||||
.replace("/", "")
|
||||
.replace(":", "")
|
||||
.replace(placeholder, "-")) # Replace the placeholder with "-"
|
||||
cluster_a_section = (
|
||||
relation[0]
|
||||
.value.lower()
|
||||
.replace(" - ", placeholder) # Replace " - " first
|
||||
.replace(" ", "-")
|
||||
.replace("/", "")
|
||||
.replace(":", "")
|
||||
.replace(placeholder, "-")
|
||||
) # Replace the placeholder with "-"
|
||||
|
||||
cluster_b_section = (relation[1].value.lower()
|
||||
.replace(" - ", placeholder) # Replace " - " first
|
||||
.replace(" ", "-")
|
||||
.replace("/", "")
|
||||
.replace(":", "")
|
||||
.replace(placeholder, "-")) # Replace the placeholder with "-"
|
||||
cluster_b_section = (
|
||||
relation[1]
|
||||
.value.lower()
|
||||
.replace(" - ", placeholder) # Replace " - " first
|
||||
.replace(" ", "-")
|
||||
.replace("/", "")
|
||||
.replace(":", "")
|
||||
.replace(placeholder, "-")
|
||||
) # Replace the placeholder with "-"
|
||||
|
||||
if cluster_b_section != "private-cluster":
|
||||
output += f'| [{relation[0].value} ({relation[0].uuid})](../../{relation[0].galaxie.json_file_name}/index.md#{cluster_a_section}) | [{relation[1].value} ({relation[1].uuid})](../../{relation[1].galaxie.json_file_name}/index.md#{cluster_b_section}) | {relation[2]} |\n'
|
||||
output += f"| [{relation[0].value} ({relation[0].uuid})](../../{relation[0].galaxie.json_file_name}/index.md#{cluster_a_section}) | [{relation[1].value} ({relation[1].uuid})](../../{relation[1].galaxie.json_file_name}/index.md#{cluster_b_section}) | {relation[2]} |\n"
|
||||
else:
|
||||
output += f'| [{relation[0].value} ({relation[0].uuid})](../../{relation[0].galaxie.json_file_name}/index.md#{cluster_a_section}) | {relation[1].value} ({relation[1].uuid}) | {relation[2]} |\n'
|
||||
output += f"| [{relation[0].value} ({relation[0].uuid})](../../{relation[0].galaxie.json_file_name}/index.md#{cluster_a_section}) | {relation[1].value} ({relation[1].uuid}) | {relation[2]} |\n"
|
||||
return output
|
||||
|
||||
def create_entry(self, cluster_dict):
|
||||
|
|
@ -326,115 +359,134 @@ class Cluster():
|
|||
galaxy_path = os.path.join(path, self.galaxie.json_file_name)
|
||||
if not os.path.exists(galaxy_path):
|
||||
os.mkdir(galaxy_path)
|
||||
relation_path = os.path.join(galaxy_path, 'relations')
|
||||
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(relation_path, f'{self.uuid}.md'), "w") as index:
|
||||
index.write(f"hide: true\n")
|
||||
with open(os.path.join(relation_path, f"{self.uuid}.md"), "w") as index:
|
||||
index.write(self._get_related_entry(related_clusters))
|
||||
|
||||
|
||||
def create_index(galaxies):
|
||||
index_output = INTRO
|
||||
index_output += STATISTICS
|
||||
for galaxie in galaxies:
|
||||
index_output += f'- [{galaxie.name}](./{galaxie.json_file_name}/index.md)\n'
|
||||
index_output += f"- [{galaxie.name}](./{galaxie.json_file_name}/index.md)\n"
|
||||
index_output += CONTRIBUTING
|
||||
return index_output
|
||||
|
||||
|
||||
def get_top_x(dict, x, big_to_small=True):
|
||||
sorted_dict = sorted(dict.items(), key=operator.itemgetter(1), reverse=big_to_small)[:x]
|
||||
sorted_dict = sorted(
|
||||
dict.items(), key=operator.itemgetter(1), reverse=big_to_small
|
||||
)[:x]
|
||||
top_x = [key for key, value in sorted_dict]
|
||||
top_x_values = sorted(dict.values(), reverse=big_to_small)[:x]
|
||||
return top_x, top_x_values
|
||||
|
||||
|
||||
def name_to_section(name):
|
||||
placeholder = "__TMP__"
|
||||
return (name.lower()
|
||||
.replace(" - ", placeholder) # Replace " - " first
|
||||
.replace(" ", "-")
|
||||
.replace("/", "")
|
||||
.replace(":", "")
|
||||
.replace(placeholder, "-")) # Replace the placeholder with "-"
|
||||
return (
|
||||
name.lower()
|
||||
.replace(" - ", placeholder) # Replace " - " first
|
||||
.replace(" ", "-")
|
||||
.replace("/", "")
|
||||
.replace(":", "")
|
||||
.replace(placeholder, "-")
|
||||
) # Replace the placeholder with "-"
|
||||
|
||||
|
||||
def create_statistics(cluster_dict):
|
||||
statistic_output = ""
|
||||
statistic_output += f'# MISP Galaxy statistics\n'
|
||||
statistic_output +='The MISP galaxy statistics are automatically generated based on the MISP galaxy JSON files. Therefore the statistics only include detailed infomration about public clusters and relations. Some statistics about private clusters and relations is included but only as an approximation based on the information gathered from the public clusters.\n'
|
||||
statistic_output += f"# MISP Galaxy statistics\n"
|
||||
statistic_output += "The MISP galaxy statistics are automatically generated based on the MISP galaxy JSON files. Therefore the statistics only include detailed infomration about public clusters and relations. Some statistics about private clusters and relations is included but only as an approximation based on the information gathered from the public clusters.\n"
|
||||
|
||||
statistic_output += f'# Cluster statistics\n'
|
||||
statistic_output += f'## Number of clusters\n'
|
||||
statistic_output += 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'
|
||||
statistic_output += f'\n'
|
||||
statistic_output += f'| No. | Type | Count {{ .pie-chart }}|\n'
|
||||
statistic_output += f'|----|------|-------|\n'
|
||||
statistic_output += f'| 1 | Public clusters | {len(public_clusters_dict)} |\n'
|
||||
statistic_output += f'| 2 | Private clusters | {len(private_clusters)} |\n'
|
||||
statistic_output += f'\n'
|
||||
statistic_output += f"# Cluster statistics\n"
|
||||
statistic_output += f"## Number of clusters\n"
|
||||
statistic_output += 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"
|
||||
statistic_output += f"\n"
|
||||
statistic_output += f"| No. | Type | Count {{ .pie-chart }}|\n"
|
||||
statistic_output += f"|----|------|-------|\n"
|
||||
statistic_output += f"| 1 | Public clusters | {len(public_clusters_dict)} |\n"
|
||||
statistic_output += f"| 2 | Private clusters | {len(private_clusters)} |\n"
|
||||
statistic_output += f"\n"
|
||||
|
||||
statistic_output += f'## Galaxies with the most clusters\n'
|
||||
statistic_output += f"## Galaxies with the most clusters\n"
|
||||
galaxy_counts = {}
|
||||
for galaxy in public_clusters_dict.values():
|
||||
galaxy_counts[galaxy] = galaxy_counts.get(galaxy, 0) + 1
|
||||
top_galaxies, top_galaxies_values = get_top_x(galaxy_counts, 20)
|
||||
statistic_output += f' | No. | Galaxy | Count {{ .log-bar-chart }}|\n'
|
||||
statistic_output += f' |----|--------|-------|\n'
|
||||
statistic_output += f" | No. | Galaxy | Count {{ .log-bar-chart }}|\n"
|
||||
statistic_output += f" |----|--------|-------|\n"
|
||||
for i, galaxy in enumerate(top_galaxies, 1):
|
||||
galaxy_section = name_to_section(galaxy.json_file_name)
|
||||
statistic_output += f' | {i} | [{galaxy.name}](../{galaxy_section}) | {top_galaxies_values[i-1]} |\n'
|
||||
statistic_output += f'\n'
|
||||
statistic_output += f" | {i} | [{galaxy.name}](../{galaxy_section}) | {top_galaxies_values[i-1]} |\n"
|
||||
statistic_output += f"\n"
|
||||
|
||||
statistic_output += f'## Galaxies with the least clusters\n'
|
||||
statistic_output += f"## Galaxies with the least clusters\n"
|
||||
flop_galaxies, flop_galaxies_values = get_top_x(galaxy_counts, 20, False)
|
||||
statistic_output += f' | No. | Galaxy | Count {{ .bar-chart }}|\n'
|
||||
statistic_output += f' |----|--------|-------|\n'
|
||||
statistic_output += f" | No. | Galaxy | Count {{ .bar-chart }}|\n"
|
||||
statistic_output += f" |----|--------|-------|\n"
|
||||
for i, galaxy in enumerate(flop_galaxies, 1):
|
||||
galaxy_section = name_to_section(galaxy.json_file_name)
|
||||
statistic_output += f' | {i} | [{galaxy.name}](../{galaxy_section}) | {flop_galaxies_values[i-1]} |\n'
|
||||
statistic_output += f'\n'
|
||||
statistic_output += f" | {i} | [{galaxy.name}](../{galaxy_section}) | {flop_galaxies_values[i-1]} |\n"
|
||||
statistic_output += f"\n"
|
||||
|
||||
statistic_output += f'# Relation statistics\n'
|
||||
statistic_output += 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'
|
||||
statistic_output += f'\n'
|
||||
statistic_output += f'## Number of relations\n'
|
||||
statistic_output += f'| No. | Type | Count {{ .pie-chart }}|\n'
|
||||
statistic_output += f'|----|------|-------|\n'
|
||||
statistic_output += f'| 1 | Public relations | {public_relations_count} |\n'
|
||||
statistic_output += f'| 2 | Private relations | {private_relations_count} |\n'
|
||||
statistic_output += f'\n'
|
||||
statistic_output += f"# Relation statistics\n"
|
||||
statistic_output += 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"
|
||||
statistic_output += f"\n"
|
||||
statistic_output += f"## Number of relations\n"
|
||||
statistic_output += f"| No. | Type | Count {{ .pie-chart }}|\n"
|
||||
statistic_output += f"|----|------|-------|\n"
|
||||
statistic_output += f"| 1 | Public relations | {public_relations_count} |\n"
|
||||
statistic_output += f"| 2 | Private relations | {private_relations_count} |\n"
|
||||
statistic_output += f"\n"
|
||||
|
||||
statistic_output += f'**Average number of relations per cluster**: {int(sum(relation_count_dict.values()) / len(relation_count_dict))}\n'
|
||||
statistic_output += f"**Average number of relations per cluster**: {int(sum(relation_count_dict.values()) / len(relation_count_dict))}\n"
|
||||
|
||||
statistic_output += f'## Cluster with the most relations\n'
|
||||
relation_count_dict_names = {cluster_dict[uuid].value: count for uuid, count in relation_count_dict.items()}
|
||||
statistic_output += f"## Cluster with the most relations\n"
|
||||
relation_count_dict_names = {
|
||||
cluster_dict[uuid].value: count for uuid, count in relation_count_dict.items()
|
||||
}
|
||||
top_25_relation, top_25_relation_values = get_top_x(relation_count_dict_names, 20)
|
||||
statistic_output += f' | No. | Cluster | Count {{ .bar-chart }}|\n'
|
||||
statistic_output += f' |----|--------|-------|\n'
|
||||
relation_count_dict_galaxies = {cluster_dict[uuid].value: cluster_dict[uuid].galaxie.json_file_name for uuid in relation_count_dict.keys()}
|
||||
statistic_output += f" | No. | Cluster | Count {{ .bar-chart }}|\n"
|
||||
statistic_output += f" |----|--------|-------|\n"
|
||||
relation_count_dict_galaxies = {
|
||||
cluster_dict[uuid].value: cluster_dict[uuid].galaxie.json_file_name
|
||||
for uuid in relation_count_dict.keys()
|
||||
}
|
||||
for i, cluster in enumerate(top_25_relation, 1):
|
||||
cluster_section = name_to_section(cluster)
|
||||
statistic_output += f' | {i} | [{cluster}](../{relation_count_dict_galaxies[cluster]}/#{cluster_section}) | {top_25_relation_values[i-1]} |\n'
|
||||
statistic_output += f'\n'
|
||||
statistic_output += f" | {i} | [{cluster}](../{relation_count_dict_galaxies[cluster]}/#{cluster_section}) | {top_25_relation_values[i-1]} |\n"
|
||||
statistic_output += f"\n"
|
||||
|
||||
statistic_output += f'# Synonyms statistics\n'
|
||||
statistic_output += f'## Cluster with the most synonyms\n'
|
||||
synonyms_count_dict_names = {cluster_dict[uuid].value: count for uuid, count in synonyms_count_dict.items()}
|
||||
statistic_output += f"# Synonyms statistics\n"
|
||||
statistic_output += f"## Cluster with the most synonyms\n"
|
||||
synonyms_count_dict_names = {
|
||||
cluster_dict[uuid].value: count for uuid, count in synonyms_count_dict.items()
|
||||
}
|
||||
top_synonyms, top_synonyms_values = get_top_x(synonyms_count_dict_names, 20)
|
||||
statistic_output += f' | No. | Cluster | Count {{ .bar-chart }}|\n'
|
||||
statistic_output += f' |----|--------|-------|\n'
|
||||
synonyms_count_dict_galaxies = {cluster_dict[uuid].value: cluster_dict[uuid].galaxie.json_file_name for uuid in synonyms_count_dict.keys()}
|
||||
statistic_output += f" | No. | Cluster | Count {{ .bar-chart }}|\n"
|
||||
statistic_output += f" |----|--------|-------|\n"
|
||||
synonyms_count_dict_galaxies = {
|
||||
cluster_dict[uuid].value: cluster_dict[uuid].galaxie.json_file_name
|
||||
for uuid in synonyms_count_dict.keys()
|
||||
}
|
||||
for i, cluster in enumerate(top_synonyms, 1):
|
||||
cluster_section = name_to_section(cluster)
|
||||
statistic_output += f' | {i} | [{cluster}](../{synonyms_count_dict_galaxies[cluster]}/#{cluster_section}) | {top_synonyms_values[i-1]} |\n'
|
||||
statistic_output += f'\n'
|
||||
statistic_output += f" | {i} | [{cluster}](../{synonyms_count_dict_galaxies[cluster]}/#{cluster_section}) | {top_synonyms_values[i-1]} |\n"
|
||||
statistic_output += f"\n"
|
||||
|
||||
return statistic_output
|
||||
|
||||
|
||||
def main():
|
||||
start_time = time.time()
|
||||
galaxies_fnames = []
|
||||
for f in os.listdir(CLUSTER_PATH):
|
||||
if '.json' in f and f not in FILES_TO_IGNORE:
|
||||
if ".json" in f and f not in FILES_TO_IGNORE:
|
||||
galaxies_fnames.append(f)
|
||||
galaxies_fnames.sort()
|
||||
|
||||
|
|
@ -442,7 +494,15 @@ def main():
|
|||
for galaxy in galaxies_fnames:
|
||||
with open(os.path.join(CLUSTER_PATH, galaxy)) as fr:
|
||||
galaxie_json = json.load(fr)
|
||||
galaxies.append(Galaxy(galaxie_json['values'], galaxie_json['authors'], galaxie_json['description'], galaxie_json['name'], galaxy.split('.')[0]))
|
||||
galaxies.append(
|
||||
Galaxy(
|
||||
galaxie_json["values"],
|
||||
galaxie_json["authors"],
|
||||
galaxie_json["description"],
|
||||
galaxie_json["name"],
|
||||
galaxy.split(".")[0],
|
||||
)
|
||||
)
|
||||
|
||||
cluster_dict = {}
|
||||
for galaxy in galaxies:
|
||||
|
|
@ -459,13 +519,14 @@ def main():
|
|||
index_output = create_index(galaxies)
|
||||
statistic_output = create_statistics(cluster_dict=cluster_dict)
|
||||
|
||||
with open(os.path.join(SITE_PATH, 'index.md'), "w") as index:
|
||||
with open(os.path.join(SITE_PATH, "index.md"), "w") as index:
|
||||
index.write(index_output)
|
||||
|
||||
with open(os.path.join(SITE_PATH, 'statistics.md'), "w") as index:
|
||||
with open(os.path.join(SITE_PATH, "statistics.md"), "w") as index:
|
||||
index.write(statistic_output)
|
||||
|
||||
print(f"Finished file creation in {time.time() - start_time} seconds")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
|
|
|||
|
|
@ -4,12 +4,20 @@ document$.subscribe(function () {
|
|||
const NODE_COLOR = "#69b3a2";
|
||||
const Parent_Node_COLOR = "#ff0000";
|
||||
|
||||
function parseFilteredTable(tf) {
|
||||
|
||||
function parseFilteredTable(tf, allData) {
|
||||
var data = [];
|
||||
tf.getFilteredData().forEach((row, i) => {
|
||||
data.push({ source: row[1][0], target: row[1][1], level: row[1][2] });
|
||||
}
|
||||
);
|
||||
sourcePath = allData[row[0] - 2].sourcePath;
|
||||
targetPath = allData[row[0] - 2].targetPath;
|
||||
data.push({
|
||||
source: row[1][0],
|
||||
sourcePath: sourcePath,
|
||||
target: row[1][1],
|
||||
targetPath: targetPath,
|
||||
level: row[1][2]
|
||||
});
|
||||
});
|
||||
return data;
|
||||
}
|
||||
|
||||
|
|
@ -18,31 +26,57 @@ document$.subscribe(function () {
|
|||
table.querySelectorAll("tr").forEach((row, i) => {
|
||||
if (i > 1) {
|
||||
var cells = row.querySelectorAll("td");
|
||||
data.push({ source: cells[0].textContent, target: cells[1].textContent, level: cells[2].textContent });
|
||||
var sourceAnchor = cells[0].querySelector("a");
|
||||
var sourcePath = sourceAnchor ? sourceAnchor.getAttribute("href") : null;
|
||||
var targetAnchor = cells[1].querySelector("a");
|
||||
var targetPath = targetAnchor ? targetAnchor.getAttribute("href") : null;
|
||||
data.push({
|
||||
source: cells[0].textContent,
|
||||
target: cells[1].textContent,
|
||||
sourcePath: sourcePath,
|
||||
targetPath: targetPath,
|
||||
level: cells[2].textContent
|
||||
});
|
||||
}
|
||||
});
|
||||
return data;
|
||||
}
|
||||
|
||||
function processNewData(newData) {
|
||||
var nodePaths = {};
|
||||
newData.forEach(d => {
|
||||
nodePaths[d.source] = d.sourcePath || null;
|
||||
nodePaths[d.target] = d.targetPath || null;
|
||||
});
|
||||
var newNodes = Array.from(new Set(newData.flatMap(d => [d.source, d.target])))
|
||||
.map(id => ({ id }));
|
||||
.map(id => ({
|
||||
id,
|
||||
path: nodePaths[id]
|
||||
}));
|
||||
|
||||
var newLinks = newData.map(d => ({ source: d.source, target: d.target }));
|
||||
return { newNodes, newLinks };
|
||||
}
|
||||
|
||||
function filterTableAndGraph(tf, simulation) {
|
||||
var filteredData = parseFilteredTable(tf);
|
||||
function filterTableAndGraph(tf, simulation, data) {
|
||||
var filteredData = parseFilteredTable(tf, data);
|
||||
var { newNodes, newLinks } = processNewData(filteredData);
|
||||
|
||||
simulation.update({ newNodes: newNodes, newLinks: newLinks });
|
||||
}
|
||||
|
||||
function createForceDirectedGraph(data, elementId) {
|
||||
// Extract nodes and links
|
||||
var nodePaths = {};
|
||||
data.forEach(d => {
|
||||
nodePaths[d.source] = d.sourcePath || null;
|
||||
nodePaths[d.target] = d.targetPath || null;
|
||||
});
|
||||
|
||||
var nodes = Array.from(new Set(data.flatMap(d => [d.source, d.target])))
|
||||
.map(id => ({ id }));
|
||||
.map(id => ({
|
||||
id,
|
||||
path: nodePaths[id]
|
||||
}));
|
||||
|
||||
var links = data.map(d => ({ source: d.source, target: d.target }));
|
||||
|
||||
|
|
@ -51,16 +85,18 @@ document$.subscribe(function () {
|
|||
.style("opacity", 0);
|
||||
|
||||
// Set up the dimensions of the graph
|
||||
var width = 1000, height = 1000;
|
||||
var width = 800, height = 1000;
|
||||
|
||||
var svg = d3.select(elementId).append("svg")
|
||||
.attr("width", width)
|
||||
.attr("height", height);
|
||||
|
||||
// Create a force simulation
|
||||
linkDistance = Math.sqrt((width * height) / nodes.length);
|
||||
|
||||
var simulation = d3.forceSimulation(nodes)
|
||||
.force("link", d3.forceLink(links).id(d => d.id).distance(10))
|
||||
.force("charge", d3.forceManyBody().strength(-20))
|
||||
.force("link", d3.forceLink(links).id(d => d.id).distance(linkDistance))
|
||||
.force("charge", d3.forceManyBody().strength(-50))
|
||||
.force("center", d3.forceCenter(width / 2, height / 2))
|
||||
.alphaDecay(0.02); // A lower value, adjust as needed
|
||||
|
||||
|
|
@ -106,6 +142,11 @@ document$.subscribe(function () {
|
|||
.style("opacity", 0);
|
||||
});
|
||||
|
||||
// Apply links on nodes
|
||||
node.on("dblclick", function (event, d) {
|
||||
location.href = d.path;
|
||||
});
|
||||
|
||||
// Define drag behavior
|
||||
var drag = d3.drag()
|
||||
.on("start", dragstarted)
|
||||
|
|
@ -150,7 +191,6 @@ document$.subscribe(function () {
|
|||
|
||||
return Object.assign(svg.node(), {
|
||||
update({ newNodes, newLinks }) {
|
||||
// Process new nodes and maintain the existing ones
|
||||
const oldNodesMap = new Map(node.data().map(d => [d.id, d]));
|
||||
nodes = newNodes.map(d => Object.assign(oldNodesMap.get(d.id) || {}, d));
|
||||
|
||||
|
|
@ -189,6 +229,14 @@ document$.subscribe(function () {
|
|||
.style("opacity", 0);
|
||||
});
|
||||
|
||||
// Apply links on nodes
|
||||
node.on("dblclick", function (event, d) {
|
||||
console.log("Node: " + d.id);
|
||||
console.log(d);
|
||||
console.log("Source Path: " + d.sourcePath);
|
||||
location.href = d.path;
|
||||
});
|
||||
|
||||
// Process new links
|
||||
const oldLinksMap = new Map(link.data().map(d => [`${d.source.id},${d.target.id}`, d]));
|
||||
links = newLinks.map(d => Object.assign(oldLinksMap.get(`${d.source.id},${d.target.id}`) || {}, d));
|
||||
|
|
@ -214,7 +262,6 @@ document$.subscribe(function () {
|
|||
document.querySelectorAll("table").forEach((table, index) => {
|
||||
var graphHeader = table.querySelector("th.graph");
|
||||
if (graphHeader) {
|
||||
// Initialize TableFilter for the table
|
||||
var tf = new TableFilter(table, {
|
||||
base_path: "../../../../01_attachements/modules/tablefilter/",
|
||||
highlight_keywords: true,
|
||||
|
|
@ -259,7 +306,7 @@ document$.subscribe(function () {
|
|||
|
||||
// Listen for table filtering events
|
||||
tf.emitter.on(['after-filtering'], function () {
|
||||
filterTableAndGraph(tf, simulation);
|
||||
filterTableAndGraph(tf, simulation, data);
|
||||
});
|
||||
}
|
||||
});
|
||||
|
|
|
|||
Loading…
Reference in a new issue