Issue 5250 - Add copyright update script

update-copyright/update_copyright.py

 #!/usr/bin/env python3
 
 import os
 import subprocess
 import re
 import datetime
 import shutil
 import urllib.parse
 import urllib.request
 import html.parser
@@ skipping 95 matching lines @@
     def handle_endtag(self, tag):
         if tag == 'tr':
             self.recordtr = False
             self.cell = 0
 
     def handle_data(self, data):
         if self.cell == 2 and self.recordtr is True:
             self.recordtr = False
             self.cell = 0
             # Only process the URL if the description is not Deprecated
-            if ('*DEPRECATED*' not in data and '(Deprecated)' not in data and
-               len(self.current_url) > 2):
+            if ('*DEPRECATED*' not in data and
+                    '(Deprecated)' not in data and
+                    len(self.current_url) > 2):
                 self.result += [self.current_url]
                 return self.result
 
 
 def extract_urls(hg_page):
     base_url = os.path.dirname(hg_page) + '/'
     parser = Parser()
     with urllib.request.urlopen(hg_page) as response:
         parser.feed(response.read().decode('utf-8'))
     parser.close()
     repo_urls = []
     for url in parser.result:
         repo_urls.append(urllib.parse.urljoin(base_url, url))
     return repo_urls
 
 
 def main(hg_page, hg_upstream):
     for repo in extract_urls(hg_page):
         process_repo(repo, hg_upstream)
 
 
 if __name__ == '__main__':
     arg_parser = argparse.ArgumentParser()
     arg_parser.add_argument('-u', '--hg-url',
-                            help='specify which Mercurial URL site to scrape',
-                            default='https://hg.adblockplus.org/')
+                            help='specify which Mercurial URL site to scrape')
     arg_parser.add_argument('-p', '--push-url',
-                            default='ssh://hg@hg.adblockplus.org/',
                             help='specify where to push the repository')
     args = arg_parser.parse_args()
-    if (args.hg_url != 'https://hg.adblockplus.org/' and args.push_url ==
-       'ssh://hg@hg.adblockplus.org/'):

[Sebastian Noack, 2017/07/07 16:58:31]

Perhaps it would be worth to handle the defaults manually, in order to avoid
duplication. It also seems to make the logic easier to follow (for me at least).

  arg_parser.add_argument('-u', '--hg-url',
                          help='specify which Mercurial URL site to scrape')
  arg_parser.add_argument('-p', '--push-url',
                          help='specify where to push the repository')
  args = arg_parser.parse_args()
  if args.hg_url and not args.push_url:
      arg_parser.error('If -u is provided, -p is mandatory')
  main(args.hg_url or 'https://hg.adblockplus.org/',
       args.push_url or 'ssh://hg@hg.adblockplus.org/')

What do you think?

[Sebastian Noack, 2017/07/17 10:19:54]

What is about this comment?

[rosie, 2017/07/17 13:23:17]

Done.

[rosie, 2017/07/17 13:23:17]

Yeah, makes sense. I like this way better.

+    if args.hg_url and not args.push_url:
         arg_parser.error('If -u is provided, -p is mandatory')
-    main(args.hg_url, args.push_url)
+    main(args.hg_url or 'https://hg.adblockplus.org/',
+         args.push_url or 'ssh://hg@hg.adblockplus.org/')