added script to detect unauthorized contributors

cla-management/detect-unauthorized-contributors

@@ -0,0 +1,75 @@
+#!/usr/bin/env python
+
+import argparse
+import requests
+import sys
+
+
+def get_usernames(contributors):
+    usernames = set()
+    for contributor in contributors:
+        usernames.add(contributor['login'])
+    return usernames
+
+
+def get_next_url(link_header):
+    # need to parse:
+    # <https://api.github.com/repositories/6650539/contributors?page=2>; rel="next", <https://api.github.com/repositories/6650539/contributors?page=3>; rel="last"
+    # <https://api.github.com/repositories/6650539/contributors?page=3>; rel="next", <https://api.github.com/repositories/6650539/contributors?page=3>; rel="last", <https://api.github.com/repositories/6650539/contributors?page=1>; rel="first", <https://api.github.com/repositories/6650539/contributors?page=1>; rel="prev"
+    # <https://api.github.com/repositories/6650539/contributors?page=1>; rel="first", <https://api.github.com/repositories/6650539/contributors?page=2>; rel="prev"
+    links = link_header.split(',')
+    for link in links:
+        (url, rel) = link.strip().split(';')
+        if rel.strip()[5:-1] == 'next':
+            return url.strip()[1:-1]
+    pass
+
+
+def get_contributors(auth):
+    url = 'https://api.github.com/repos/neo4j/neo4j/contributors'
+    try:
+        contributors = []
+        while url is not None:
+            response = requests.get(url, auth=auth)
+            response.raise_for_status()
+            contributors += response.json( )
+            url = get_next_url(response.headers['Link'])
+        return get_usernames(contributors)
+    except requests.exceptions.HTTPError as e:
+        if e.response.status_code == requests.codes.forbidden and e.response.headers['X-RateLimit-Remaining'] == '0':
+            exit("Failed to get list of contributors from GitHub due to rate limiting.")
+
+        print >> sys.stderr, "Failed to obtain pull request details from GitHub API."
+        print >> sys.stderr, "url: %s" % url
+        print >> sys.stderr, "response status: %s" % e.response.status_code
+        print >> sys.stderr, "headers:"
+        for header in e.response.headers:
+            print >> sys.stderr, "\t%s: %s" % (header, e.response.headers[header])
+        print >> sys.stderr, "body: %s" % e.response.text
+        exit(1)
+
+
+def get_whitelisted_users(whitelist):
+    usernames = set()
+    if len(whitelist.strip()) == 0:
+        return usernames
+    for username in whitelist.split(','):
+        usernames.add(username.strip())
+    return usernames
+
+
+parser = argparse.ArgumentParser(description='Ensure all contributors to the product have been whitelisted')
+parser.add_argument('whitelist', help='Comma-separated list of GitHub usernames')
+parser.add_argument('--username', help='GitHub username, to avoid rate limit')
+parser.add_argument('--password', help='GitHub password, to avoid rate limit')
+args = parser.parse_args()
+
+auth = None
+if args.username is not None and args.password is not None:
+    auth = (args.username, args.password)
+
+contributors = get_contributors(auth)
+whitelisted_users = get_whitelisted_users(args.whitelist)
+
+if not contributors.issubset(whitelisted_users):
+    exit("Users [%s] were not in the whitelist." % ", ".join(contributors.difference(whitelisted_users)))