Rietveld Code Review Tool
Help | Bug tracker | Discussion group | Source code

Unified Diff: update-copyright/update_copyright.py

Issue 29459580: Issue 5250 - Add copyright update script (Closed) Base URL: https://hg.adblockplus.org/codingtools
Patch Set: Also test strings and non-eyeo copyright info Created July 7, 2017, 3:55 p.m.
Use n/p to move between diff chunks; N/P to move between comments.
Jump to:
View side-by-side diff with in-line comments
Download patch
« no previous file with comments | « update-copyright/tox.ini ('k') | no next file » | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: update-copyright/update_copyright.py
===================================================================
new file mode 100755
--- /dev/null
+++ b/update-copyright/update_copyright.py
@@ -0,0 +1,148 @@
+#!/usr/bin/env python3
+
+import os
+import subprocess
+import re
+import datetime
+import shutil
+import urllib.parse
+import urllib.request
+import html.parser
+import argparse
+
+
+CURRENT_YEAR = datetime.datetime.now().year
+
+
+def process_repo(url, hg_upstream):
+ repo = url.rstrip('/').split('/')[-1]
+
+ if repo in {
+ # headers are copied from libadblockplus, no need to update seperately
+ 'libadblockplus-binaries',
+ # huge and only contains autogenerated builds
+ 'downloads',
+ }:
+ return
+
+ try:
+ subprocess.check_call(['hg', 'clone', url, repo])
+ if repo == 'adblockbrowser':
+ # adblockbrowser is a FF fork with its own changes in a
+ # seperate branch
+ subprocess.check_call(['hg', 'up', '--rev', 'adblockbrowser',
+ '--repository', repo])
+ else:
+ # switch to 'master' bookmark if it exists
+ subprocess.call(['hg', 'up', '--rev', 'master',
+ '--repository', repo])
+ for dirpath, dirnames, filenames in os.walk(repo):
+ if dirpath == repo:
+ dirnames.remove('.hg')
+
+ for filename in filenames:
+ text_replace(dirpath, filename)
+ if hg_upstream is None:
+ hg_upstream = url
+ else:
+ hg_upstream += '/' + repo
+ hg_commit(repo, hg_upstream)
+
+ 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:
+ 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()
+
+
+def hg_commit(repo, hg_upstream):
+ try:
+ subprocess.check_call(['hg', 'commit', '-m',
+ 'Noissue - Updated copyright year',
+ '--repository', repo])
+ except subprocess.CalledProcessError as e:
+ if e.returncode == 1: # no changes
+ return
+ raise
+
+ # Push changes, or save patch if access denied
+ if subprocess.call(['hg', 'push', '--repository', repo, hg_upstream]) != 0:
+ with open(repo + '.patch', 'wb') as file:
+ print('couldnt push, making patch instead')
+ subprocess.check_call(['hg', 'export', '--repository', repo],
+ stdout=file)
+
+
+class Parser(html.parser.HTMLParser):
+ result = []
+ recordtr = False
+ cell = 0
+ current_url = ''
+
+ def handle_starttag(self, tag, attrs):
+ if tag == 'tr':
+ self.recordtr = True
+ if tag == 'td':
+ self.cell += 1
+ if tag == 'a':
+ attrs = dict(attrs)
+ if 'list' in attrs.get('class', '').split():
+ self.current_url = attrs['href']
+
+ 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):
Sebastian Noack 2017/07/07 16:05:27 The indentation is off by one character here. Exam
Sebastian Noack 2017/07/07 16:58:29 It seems you missed this comment.
Sebastian Noack 2017/07/17 10:19:53 It seems this comment still hasn't been addressed.
rosie 2017/07/17 13:23:16 Done.
rosie 2017/07/17 13:23:16 I was getting a flake8 error when using the proper
+ 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',
+ required=True)
+ 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)
« no previous file with comments | « update-copyright/tox.ini ('k') | no next file » | no next file with comments »

Powered by Google App Engine
This is Rietveld