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 40 matching lines @@
     finally:
         shutil.rmtree(repo, ignore_errors=True)
 
 
 def text_replace(dirpath, filename):
     with open(os.path.join(dirpath, filename), 'r+',
               encoding='utf-8', newline='') as file:
         try:
             text = file.read()
         except UnicodeDecodeError:
-            print("Error: Couldn't read {}{}".format(dirpath, filename))
             return
 
         text = re.sub(
             r'(copyright.*?\d{4})(?:-\d{4})?\s+eyeo gmbh',
             r'\1-{} eyeo GmbH'.format(CURRENT_YEAR), text, 0, re.I
         )
         file.seek(0)
         file.write(text)
         file.truncate()
 
@@ skipping 35 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
-            deprecated = (re.search(r'\*DEPRECATED\*', data) or
-                          re.search(r'(Deprecated)', data))
-            if not deprecated 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',
-                            default=None,

[Vasily Kuznetsov, 2017/07/04 15:02:40]

I think you don't need a default here since `-u` is a required argument.

[rosie, 2017/07/04 15:14:02]

Done.

-                            help='specify which Mercurial URL site to scrape',
-                            required=True)
+                            help='specify which Mercurial URL site to scrape')
     arg_parser.add_argument('-p', '--push-url',
-                            default=None,
                             help='specify where to push the repository')
     args = arg_parser.parse_args()
-    main(args.hg_url, args.push_url)
+    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/')