Fix Semgrep findings in Python tooling (#5899)

- generate_docset.py: use SHA-256 instead of SHA-1 for the cache file
  name digest of downloaded images.
- generate_docset.py: suppress dynamic-urllib-use-detected; the URL
  scheme is restricted to http(s) right before the call.
- generate_natvis.py: suppress direct-use-of-jinja2; the template
  renders a local XML file with autoescape enabled.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

docs/docset/generate_docset.py

@@ -341,13 +341,14 @@ def download(url, docs) -> str:
         raise ValueError(f'not an http(s) URL: {url}')
     req = urllib.request.Request(u.geturl(), headers={'User-Agent': USER_AGENT})
     # (the scheme is checked above)
+    # nosemgrep: python.lang.security.audit.dynamic-urllib-use-detected.dynamic-urllib-use-detected
     with urllib.request.urlopen(req, timeout=20) as r:  # nosec B310
         data = r.read()
         ctype = r.headers.get_content_type()
     path = urllib.parse.unquote(u.path).lstrip('/')
     ext = os.path.splitext(path)[1]
     if u.query or not ext or path.endswith('/'):
-        digest = hashlib.sha1(url.encode(), usedforsecurity=False).hexdigest()[:12]
+        digest = hashlib.sha256(url.encode()).hexdigest()[:12]
         path = os.path.join(os.path.dirname(path), digest + CONTENT_TYPE_EXT.get(ctype, ext or '.bin'))
     rel = os.path.normpath(os.path.join('assets', 'external', u.hostname, path))
     out = os.path.join(docs, rel)

tools/generate_natvis/generate_natvis.py

@@ -139,9 +139,12 @@ if __name__ == '__main__':
 
     namespaces += [f'{namespaces[0]}::{ns}' for ns in inline_namespaces]
 
+    # The template renders a local XML file, not a web response, and autoescape is enabled.
+    # nosemgrep: python.flask.security.xss.audit.direct-use-of-jinja2.direct-use-of-jinja2
     env = jinja2.Environment(loader=jinja2.FileSystemLoader(searchpath=sys.path[0]), autoescape=True, trim_blocks=True,
                                                             lstrip_blocks=True, keep_trailing_newline=True)
     template = env.get_template('nlohmann_json.natvis.j2')
+    # nosemgrep: python.flask.security.xss.audit.direct-use-of-jinja2.direct-use-of-jinja2
     natvis = template.render(namespaces=namespaces)
 
     output = args.output or os.path.join(args.repo_root, 'nlohmann_json.natvis')