hohn/codeql
1
0
Fork 0
mirror of https://github.com/github/codeql.git synced 2025-12-16 16:53:25 +01:00
Code Issues Packages Projects Releases Wiki Activity

MaD generator: really fix ordering problem

Browse Source
This commit is contained in:
Paolo Tranquilli
2025-06-13 08:45:55 +02:00
parent f7266c973b
commit 1a36374718
1 changed files with 10 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
misc/scripts/models-as-data/bulk_generate_mad.py
View File

@@ -236,7 +236,6 @@ def generate_models(config, args, project: Project, database_dir: str) -> None:
language = config["language"]
generator = mad.Generator(language)
# Note: The argument parser converts with-sinks to with_sinks, etc.
generator.generateSinks = should_generate_sinks(project)
generator.generateSources = should_generate_sources(project)
generator.generateSummaries = should_generate_summaries(project)
@@ -348,7 +347,7 @@ def download_dca_databases(
"""
print("\n=== Finding projects ===")
project_map = {project["name"]: project for project in projects}
analyzed_databases = {}
analyzed_databases = {n: None for n in project_map}
for experiment_name in experiment_names:
response = get_json_from_github(
f"https://raw.githubusercontent.com/github/codeql-dca-main/data/{experiment_name}/reports/downloads.json",
@@ -361,17 +360,24 @@ def download_dca_databases(
artifact_name = analyzed_database["artifact_name"]
pretty_name = pretty_name_from_artifact_name(artifact_name)
if not pretty_name in project_map:
if not pretty_name in analyzed_databases:
print(f"Skipping {pretty_name} as it is not in the list of projects")
continue
if pretty_name in analyzed_databases:
if analyzed_databases[pretty_name] is not None:
print(
f"Skipping previous database {analyzed_databases[pretty_name]['artifact_name']} for {pretty_name}"
)
analyzed_databases[pretty_name] = analyzed_database
not_found = [name for name, db in analyzed_databases.items() if db is None]
if not_found:
print(
f"ERROR: The following projects were not found in the DCA experiments: {', '.join(not_found)}"
)
sys.exit(1)
def download_and_decompress(analyzed_database: dict) -> str:
artifact_name = analyzed_database["artifact_name"]
repository = analyzed_database["repository"]