scripts: prepare for giving credit for contributions that have been integrated into other changesets

scripts/contributor_data.py

@@ -1,90 +1,96 b''
 # -*- coding: utf-8 -*-
 
 # Some committers are so wrong that it doesn't point at any contributor:
 total_ignore = set()
 total_ignore.add('*** failed to import extension hggit: No module named hggit')
 total_ignore.add('<>')
 
 # Normalize some committer names where people have contributed under different
 # names or email addresses:
 name_fixes = {}
 name_fixes['Andrew Shadura'] = "Andrej Shadura <[e-mail]>"
 name_fixes['aparkar'] = "Aparkar <[e-mail]>"
 name_fixes['Aras Pranckevicius'] = "Aras Pranckevičius <[e-mail]>"
 name_fixes['Augosto Hermann'] = "Augusto Herrmann <[e-mail]>"
 name_fixes['"Bradley M. Kuhn" <[e-mail]>'] = "Bradley M. Kuhn <[e-mail]>"
 name_fixes['dmitri.kuznetsov'] = "Dmitri Kuznetsov"
 name_fixes['Dmitri Kuznetsov'] = "Dmitri Kuznetsov"
 name_fixes['domruf'] = "Dominik Ruf <[e-mail]>"
 name_fixes['Ingo von borstel'] = "Ingo von Borstel <[e-mail]>"
 name_fixes['Jan Heylen'] = "Jan Heylen <[e-mail]>"
 name_fixes['Jason F. Harris'] = "Jason Harris <[e-mail]>"
 name_fixes['Jelmer Vernooij'] = "Jelmer Vernooij <[e-mail]>"
 name_fixes['jfh <[e-mail]>'] = "Jason Harris <[e-mail]>"
 name_fixes['Leonardo Carneiro<[e-mail]>'] = "Leonardo Carneiro <[e-mail]>"
 name_fixes['leonardo'] = "Leonardo Carneiro <[e-mail]>"
 name_fixes['Leonardo <[e-mail]>'] = "Leonardo Carneiro <[e-mail]>"
 name_fixes['Les Peabody'] = "Les Peabody <[e-mail]>"
 name_fixes['"Lorenzo M. Catucci" <[e-mail]>'] = "Lorenzo M. Catucci <[e-mail]>"
 name_fixes['Lukasz Balcerzak'] = "Łukasz Balcerzak <[e-mail]>"
 name_fixes['mao <[e-mail]>'] = "Ching-Chen Mao <[e-mail]>"
 name_fixes['marcink'] = "Marcin Kuźmiński <[e-mail]>"
 name_fixes['Marcin Kuzminski'] = "Marcin Kuźmiński <[e-mail]>"
 name_fixes['[e-mail]'] = "nansenat16 <[e-mail]>"
 name_fixes['Peter Vitt'] = "Peter Vitt <[e-mail]>"
 name_fixes['[e-mail]'] = "Philip Jameson <[e-mail]>"
 name_fixes['Søren Løvborg'] = "Søren Løvborg <[e-mail]>"
 name_fixes['Thomas De Schampheleire'] = "Thomas De Schampheleire <[e-mail]>"
 name_fixes['Hosted Weblate'] = "<>"
 name_fixes['Weblate'] = "<>"
 name_fixes['xpol'] = "xpol <[e-mail]>"
 name_fixes['Lars <[e-mail]>'] = "Lars Kruse <[e-mail]>"
 
 # Some committer email address domains that indicate that another entity might
 # hold some copyright too:
 domain_extra = {}
 domain_extra['unity3d.com'] = "Unity Technologies"
 domain_extra['rhodecode.com'] = "RhodeCode GmbH"
 
 # Repository history show some old contributions that traditionally hasn't been
 # listed in about.html - preserve that:
 no_about = set(total_ignore)
 # The following contributors were traditionally not listed in about.html and it
 # seems unclear if the copyright is personal or belongs to a company.
 no_about.add(('Thayne Harbaugh <[e-mail]>', '2011'))
 no_about.add(('Dies Koper <[e-mail]>', '2012'))
 no_about.add(('Erwin Kroon <[e-mail]>', '2012'))
 no_about.add(('Vincent Caron <[e-mail]>', '2012'))
 # These contributors' contributions might be too small to be copyrightable:
 no_about.add(('[e-mail]', '2012'))
 no_about.add(('Stefan Engel <[e-mail]>', '2012'))
 no_about.add(('Ton Plomp <[e-mail]>', '2013'))
 # Was reworked and contributed later and shadowed by other contributions:
 no_about.add(('Sean Farley <[e-mail]>', '2013'))
 
+# Contributors in about.html and CONTRIBUTORS not appearing in repository
+# history:
+other = [
+    # Work folded into commits attributed to others:
+]
+
 # Preserve contributors listed in about.html but not appearing in repository
 # history:
 other_about = [
     ("2011", "Aparkar <[e-mail]>"),
     ("2010", "RhodeCode GmbH"),
     ("2011", "RhodeCode GmbH"),
     ("2012", "RhodeCode GmbH"),
     ("2013", "RhodeCode GmbH"),
 ]
 
 # Preserve contributors listed in CONTRIBUTORS but not appearing in repository
 # history:
 other_contributors = [
     ("", "Andrew Kesterson <[e-mail]>"),
     ("", "cejones"),
     ("", "David A. Sjøen <[e-mail]>"),
     ("", "James Rhodes <[e-mail]>"),
     ("", "Jonas Oberschweiber <[e-mail]>"),
     ("", "larikale"),
     ("", "RhodeCode GmbH"),
     ("", "Sebastian Kreutzberger <[e-mail]>"),
     ("", "Steve Romanow <[e-mail]>"),
     ("", "SteveCohen"),
     ("", "Thomas <[e-mail]>"),
     ("", "Thomas Waldmann <[e-mail]>"),
 ]

scripts/update-copyrights.py

@@ -1,164 +1,164 b''
 #!/usr/bin/env python2
 # -*- coding: utf-8 -*-
 
 """
 Kallithea script for maintaining contributor lists from version control
 history.
 
 This script and the data in it is a best effort attempt at reverse engineering
 previous attributions and correlate that with version control history while
 preserving all existing copyright statements and attribution. This script is
 processing and summarizing information found elsewhere - it is not by itself
 making any claims. Comments in the script are an attempt at reverse engineering
 possible explanations - they are not showing any intent or confirming it is
 correct.
 
 Three files are generated / modified by this script:
 
 kallithea/templates/about.html claims to show copyright holders, and the GPL
 license requires such existing "legal notices" to be preserved. We also try to
 keep it updated with copyright holders, but do not claim it is a correct list.
 
 CONTRIBUTORS has the purpose of giving credit where credit is due and list all
 the contributor names in the source.
 
 kallithea/templates/base/base.html contains the copyright years in the page
 footer.
 
 Both make a best effort of listing all copyright holders, but revision control
 history might be a better and more definitive source.
 
 Contributors are sorted "fairly" by copyright year and amount of
 contribution.
 
 New contributors are listed, without considering if the contribution contains
 copyrightable work.
 
 When the copyright might belong to a different legal entity than the
 contributor, the legal entity is given credit too.
 """
 
 import os
 import re
 from collections import defaultdict
 import contributor_data
 
 
 def sortkey(x):
     """Return key for sorting contributors "fairly":
     * latest contribution
     * first contribution
     * number of contribution years
     * name (with some unicode normalization)
     The entries must be 2-tuples of a list of string years and the unicode name"""
     return (x[0] and -int(x[0][-1]),
             x[0] and int(x[0][0]),
             -len(x[0]),
             x[1].decode('utf-8').lower().replace(u'\xe9', u'e').replace(u'\u0142', u'l')
         )
 
 
 def nice_years(l, dash='-', join=' '):
     """Convert a list of years into brief range like '1900-1901, 1921'."""
     if not l:
         return ''
     start = end = int(l[0])
     ranges = []
     for year in l[1:] + [0]:
         year = int(year)
         if year == end + 1:
             end = year
             continue
         if start == end:
             ranges.append('%s' % start)
         else:
             ranges.append('%s%s%s' % (start, dash, end))
         start = end = year
     assert start == 0 and end == 0, (start, end)
     return join.join(ranges)
 
 
 def insert_entries(
         filename,
         all_entries,
         no_entries,
         domain_extra,
         split_re,
         normalize_name,
         format_f):
     """Update file with contributor information.
     all_entries: list of tuples with year and name
     no_entries: set of names or name and year tuples to ignore
     domain_extra: map domain name to extra credit name
     split_re: regexp matching the part of file to rewrite
     normalize_name: function to normalize names for grouping and display
     format_f: function formatting year list and name to a string
     """
     name_years = defaultdict(set)
 
     for year, name in all_entries:
         if name in no_entries or (name, year) in no_entries:
             continue
         domain = name.split('@', 1)[-1].rstrip('>')
         if domain in domain_extra:
             name_years[domain_extra[domain]].add(year)
         name_years[normalize_name(name)].add(year)
 
     l = [(list(sorted(year for year in years if year)), name)
          for name, years in name_years.items()]
     l.sort(key=sortkey)
 
     with open(filename) as f:
         pre, post = re.split(split_re, f.read())
 
     with open(filename, 'w') as f:
         f.write(pre +
                 ''.join(format_f(years, name) for years, name in l) +
                 post)
 
 
 def main():
     repo_entries = [
         (year, contributor_data.name_fixes.get(name) or contributor_data.name_fixes.get(name.rsplit('<', 1)[0].strip()) or name)
         for year, name in
         (line.strip().split(' ', 1)
          for line in os.popen("""hg log -r '::.' -T '{date(date,"%Y")} {author}\n'""").readlines())
         ]
 
     insert_entries(
         filename='kallithea/templates/about.html',
-        all_entries=repo_entries + contributor_data.other_about,
+        all_entries=repo_entries + contributor_data.other_about + contributor_data.other,
         no_entries=contributor_data.no_about,
         domain_extra=contributor_data.domain_extra,
         split_re=r'(?:  <li>Copyright &copy; [^\n]*</li>\n)*',
         normalize_name=lambda name: name.split('<', 1)[0].strip(),
         format_f=lambda years, name: '  <li>Copyright &copy; %s, %s</li>\n' % (nice_years(years, '&ndash;', ', '), name),
         )
 
     insert_entries(
         filename='CONTRIBUTORS',
-        all_entries=repo_entries + contributor_data.other_contributors,
+        all_entries=repo_entries + contributor_data.other_contributors + contributor_data.other,
         no_entries=contributor_data.total_ignore,
         domain_extra=contributor_data.domain_extra,
         split_re=r'(?:    [^\n]*\n)*',
         normalize_name=lambda name: name,
         format_f=lambda years, name: ('    %s%s%s\n' % (name, ' ' if years else '', nice_years(years))),
         )
 
     insert_entries(
         filename='kallithea/templates/base/base.html',
         all_entries=repo_entries,
         no_entries=contributor_data.total_ignore,
         domain_extra={},
         split_re=r'(?<=&copy;) .* (?=by various authors)',
         normalize_name=lambda name: '',
         format_f=lambda years, name: ' ' + nice_years(years, '&ndash;', ', ') + ' ',
         )
 
 
 if __name__ == '__main__':
     main()
 
 
 # To list new contributors since last tagging:
 # { hg log -r '::tagged()' -T '    {author}\n    {author}\n'; hg log -r '::.' -T '    {author}\n' | sort | uniq; } | sort | uniq -u